{"_id":"ai-vision-mcp","_rev":"21-cb273e270bb8d8067682263499581154","name":"ai-vision-mcp","dist-tags":{"beta":"0.0.4-beta","latest":"0.0.7","dev":"0.0.7-dev.1"},"versions":{"0.0.1":{"name":"ai-vision-mcp","version":"0.0.1","keywords":["mcp","vision","ai","image-analysis","video-analysis","gemini","vertex-ai","google-ai"],"author":{"name":"Your Name","email":"your.email@example.com"},"license":"MIT","_id":"ai-vision-mcp@0.0.1","maintainers":[{"name":"tan-yong-sheng","email":"tys203831@gmail.com"}],"homepage":"https://github.com/tan-yong-sheng/ai-vision-mcp#readme","bugs":{"url":"https://github.com/tan-yong-sheng/ai-vision-mcp/issues"},"bin":{"ai-vision-mcp":"dist/index.js"},"dist":{"shasum":"f0eafef7ac4b70c63400db8afcfc031de3433bff","tarball":"https://registry.npmjs.org/ai-vision-mcp/-/ai-vision-mcp-0.0.1.tgz","fileCount":123,"integrity":"sha512-7s4RoJdp79kW6M4Hmbth9L6P+zq/TfkwiKp9UWeDtnb+GARdByfu090AIpRtQzkk/OKEabZdTFJn9uNi2GYC6g==","signatures":[{"sig":"MEQCIBrEB9zsKbC3npeQW4vVwOTlVFnbQ2IVkt/4VblRWVKwAiBQSW6IJED6JByXFKJ7dALwIoHWMrD9o6rO0ok9vVHc/Q==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":280911},"main":"dist/index.js","type":"module","types":"./dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"cf0438a4651cdb8f4c1ee89bcb88ae92ad708537","scripts":{"dev":"tsc --watch","lint":"eslint src/**/*.ts","build":"tsc","start":"node dist/index.js","format":"prettier --write src/**/*.ts","prepare":"npm run build","version":"npm run format && git add -A src","lint:fix":"eslint src/**/*.ts --fix","preversion":"npm run lint","postversion":"git push && git push --tags","prepublishOnly":"npm run lint"},"_npmUser":{"name":"tan-yong-sheng","email":"tys203831@gmail.com"},"repository":{"url":"git+https://github.com/tan-yong-sheng/ai-vision-mcp.git","type":"git"},"_npmVersion":"10.9.3","description":"Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI","directories":{},"_nodeVersion":"22.19.0","dependencies":{"zod":"^3.23.8","dotenv":"^16.4.5","mime-types":"^2.1.35","node-fetch":"^3.3.2","@google/genai":"^1.0.0","@aws-sdk/client-s3":"^3.901.0","@google-cloud/storage":"^7.17.1","@google-cloud/vertexai":"^1.0.0","@modelcontextprotocol/sdk":"^1.0.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"eslint":"^8.57.0","prettier":"^3.3.2","typescript":"^5.5.0","@types/node":"^20.14.0","@types/mime-types":"^2.1.4","eslint-config-prettier":"^9.1.2","eslint-plugin-prettier":"^5.5.4","@typescript-eslint/parser":"^7.18.0","@typescript-eslint/eslint-plugin":"^7.18.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-vision-mcp_0.0.1_1759673822584_0.7219737194848479","host":"s3://npm-registry-packages-npm-production"}},"0.0.2":{"name":"ai-vision-mcp","version":"0.0.2","keywords":["mcp","vision","ai","image-analysis","video-analysis","gemini","vertex-ai","google-ai"],"author":{"name":"Your Name","email":"your.email@example.com"},"license":"MIT","_id":"ai-vision-mcp@0.0.2","maintainers":[{"name":"tan-yong-sheng","email":"tys203831@gmail.com"}],"homepage":"https://github.com/tan-yong-sheng/ai-vision-mcp#readme","bugs":{"url":"https://github.com/tan-yong-sheng/ai-vision-mcp/issues"},"bin":{"ai-vision-mcp":"dist/index.js"},"dist":{"shasum":"48e7e3cc83ee238e3aa706de92cb698302a3e374","tarball":"https://registry.npmjs.org/ai-vision-mcp/-/ai-vision-mcp-0.0.2.tgz","fileCount":127,"integrity":"sha512-HcCU34Xm1EluGxEaYCxWAtKsnPgUfaGVbRS4ceorZPiW9UWjwXmba5RXXeTrxo0PqyhmMaYlE7j1Aj+zSMbptg==","signatures":[{"sig":"MEUCIQDbmzxYUm3nrQfeExc3XIVeNPovSBPzj/4cA6vt4s9NZQIgUU1ArDVkDYF34vAeaP881FBAL5ofRIpGBFXndgUoq/8=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":308793},"main":"dist/index.js","type":"module","types":"./dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"01d1c8c6cd01889f20abe7b7e26229897f6da402","scripts":{"dev":"tsc --watch","lint":"eslint src/**/*.ts","build":"tsc","start":"node dist/index.js","format":"prettier --write src/**/*.ts","prepare":"npm run build","version":"npm run format && git add -A src","lint:fix":"eslint src/**/*.ts --fix","preversion":"npm run lint","postversion":"git push && git push --tags","prepublishOnly":"npm run lint"},"_npmUser":{"name":"tan-yong-sheng","email":"tys203831@gmail.com"},"repository":{"url":"git+https://github.com/tan-yong-sheng/ai-vision-mcp.git","type":"git"},"_npmVersion":"10.9.3","description":"Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI","directories":{},"_nodeVersion":"22.19.0","dependencies":{"zod":"^3.23.8","dotenv":"^16.4.5","mime-types":"^2.1.35","node-fetch":"^3.3.2","@google/genai":"^1.0.0","@aws-sdk/client-s3":"^3.901.0","@google-cloud/storage":"^7.17.1","@google-cloud/vertexai":"^1.0.0","@modelcontextprotocol/sdk":"^1.0.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"eslint":"^8.57.0","prettier":"^3.3.2","typescript":"^5.5.0","@types/node":"^20.14.0","@types/mime-types":"^2.1.4","eslint-config-prettier":"^9.1.2","eslint-plugin-prettier":"^5.5.4","@typescript-eslint/parser":"^7.18.0","@typescript-eslint/eslint-plugin":"^7.18.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-vision-mcp_0.0.2_1759720505446_0.8019415742705773","host":"s3://npm-registry-packages-npm-production"}},"0.0.3":{"name":"ai-vision-mcp","version":"0.0.3","keywords":["mcp","vision","ai","image-analysis","video-analysis","gemini","vertex-ai","google-ai"],"author":{"name":"Your Name","email":"your.email@example.com"},"license":"MIT","_id":"ai-vision-mcp@0.0.3","maintainers":[{"name":"tan-yong-sheng","email":"tys203831@gmail.com"}],"homepage":"https://github.com/tan-yong-sheng/ai-vision-mcp#readme","bugs":{"url":"https://github.com/tan-yong-sheng/ai-vision-mcp/issues"},"bin":{"ai-vision-mcp":"dist/index.js"},"dist":{"shasum":"7a65ff0eeb4ec925b1556bf07e17d4125bd176e9","tarball":"https://registry.npmjs.org/ai-vision-mcp/-/ai-vision-mcp-0.0.3.tgz","fileCount":143,"integrity":"sha512-vcZGPbKCAk/FMCl1ee3MkCmsyNQg+OGD4Zrk2fAu436HETDBIA7OjidkX8JkvBjERTfCCq+SekA8jC2h1tkcbg==","signatures":[{"sig":"MEYCIQDWjCXZSgY8/SI1jUiv/yV4Msh8FNTtn+kHU2m6w+OeZgIhAISndj4XxRatEqgAhEWpAw3rfb5M9f30soIjL50V2xN4","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":438433},"main":"dist/index.js","type":"module","types":"./dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"92283f7c2b0f0fde8a3d582c639fc739ae427c1d","scripts":{"dev":"tsc --watch","lint":"eslint src/**/*.ts","build":"tsc","start":"node dist/index.js","format":"prettier --write src/**/*.ts","prepare":"npm run build","version":"npm run format && git add -A src","lint:fix":"eslint src/**/*.ts --fix","preversion":"npm run lint","postversion":"git push && git push --tags","prepublishOnly":"npm run lint"},"_npmUser":{"name":"tan-yong-sheng","email":"tys203831@gmail.com"},"repository":{"url":"git+https://github.com/tan-yong-sheng/ai-vision-mcp.git","type":"git"},"_npmVersion":"10.9.3","description":"Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI","directories":{},"_nodeVersion":"22.19.0","dependencies":{"zod":"^3.23.8","sharp":"^0.33.5","dotenv":"^16.4.5","mime-types":"^2.1.35","node-fetch":"^3.3.2","@google/genai":"^1.0.0","@aws-sdk/client-s3":"^3.901.0","@google-cloud/storage":"^7.17.1","@modelcontextprotocol/sdk":"^1.0.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"eslint":"^8.57.0","prettier":"^3.3.2","@types/ws":"^8.18.1","typescript":"^5.5.0","@types/glob":"^8.1.0","@types/long":"^4.0.2","@types/node":"^20.14.0","@types/yauzl":"^2.10.3","@types/phoenix":"^1.6.6","@types/mime-types":"^2.1.4","@types/html-to-text":"^9.0.4","eslint-config-prettier":"^9.1.2","eslint-plugin-prettier":"^5.5.4","@typescript-eslint/parser":"^7.18.0","@types/http-cache-semantics":"^4.0.4","@typescript-eslint/eslint-plugin":"^7.18.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-vision-mcp_0.0.3_1760090781594_0.4838316804988616","host":"s3://npm-registry-packages-npm-production"}},"0.0.4":{"name":"ai-vision-mcp","version":"0.0.4","keywords":["mcp","vision","ai","image-analysis","video-analysis","gemini","vertex-ai","google-ai"],"author":{"name":"Your Name","email":"your.email@example.com"},"license":"MIT","_id":"ai-vision-mcp@0.0.4","maintainers":[{"name":"tan-yong-sheng","email":"tys203831@gmail.com"}],"homepage":"https://github.com/tan-yong-sheng/ai-vision-mcp#readme","bugs":{"url":"https://github.com/tan-yong-sheng/ai-vision-mcp/issues"},"bin":{"ai-vision-mcp":"dist/index.js"},"dist":{"shasum":"539e00600c9d91158f5f2af4301105e81d74aead","tarball":"https://registry.npmjs.org/ai-vision-mcp/-/ai-vision-mcp-0.0.4.tgz","fileCount":143,"integrity":"sha512-fA5rogW2kdIH1RsZb7QLKdrLS0NHCMNKrCnsBBqveNTFIlCDwF3WfZualaaty1BkOs7oCqtBr848peAq5E91/Q==","signatures":[{"sig":"MEUCIQDN/2ai4m14EkWyAxtuCQz7apXkhu9G3WA+hpodg/J7yQIgVfGHXdrtoD7NzFooYT89tucW++Ukm/Emoz/1OiWrlgw=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":443181},"main":"dist/index.js","type":"module","types":"./dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"356975611f9fb5a860adfa2f695607f3f422124e","scripts":{"dev":"tsc --watch","lint":"eslint src/**/*.ts","build":"tsc","start":"node dist/index.js","format":"prettier --write src/**/*.ts","prepare":"npm run build","version":"npm run format && git add -A src","lint:fix":"eslint src/**/*.ts --fix","preversion":"npm run lint","postversion":"git push && git push --tags","prepublishOnly":"npm run lint","validate-server":"ajv validate -s https://registry.modelcontextprotocol.org/schemas/server-schema.json -d server.json","publish-registry":"mcp-publisher publish","publish-registry:dry-run":"mcp-publisher publish --dry-run"},"_npmUser":{"name":"tan-yong-sheng","email":"tys203831@gmail.com"},"repository":{"url":"git+https://github.com/tan-yong-sheng/ai-vision-mcp.git","type":"git"},"_npmVersion":"10.9.3","description":"Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI","directories":{},"_nodeVersion":"22.19.0","dependencies":{"zod":"^3.23.8","sharp":"^0.33.5","dotenv":"^16.4.5","mime-types":"^2.1.35","node-fetch":"^3.3.2","@google/genai":"^1.0.0","@aws-sdk/client-s3":"^3.901.0","@google-cloud/storage":"^7.17.1","@modelcontextprotocol/sdk":"^1.0.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"eslint":"^8.57.0","ajv-cli":"^5.0.0","prettier":"^3.3.2","@types/ws":"^8.18.1","typescript":"^5.5.0","@types/glob":"^8.1.0","@types/long":"^4.0.2","@types/node":"^20.14.0","@types/yauzl":"^2.10.3","@types/phoenix":"^1.6.6","@types/mime-types":"^2.1.4","@types/html-to-text":"^9.0.4","eslint-config-prettier":"^9.1.2","eslint-plugin-prettier":"^5.5.4","@typescript-eslint/parser":"^7.18.0","@types/http-cache-semantics":"^4.0.4","@typescript-eslint/eslint-plugin":"^7.18.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-vision-mcp_0.0.4_1760156862743_0.4953604022794218","host":"s3://npm-registry-packages-npm-production"}},"0.0.4-beta":{"name":"ai-vision-mcp","version":"0.0.4-beta","keywords":["mcp","vision","ai","image-analysis","video-analysis","gemini","vertex-ai","google-ai"],"author":{"name":"Your Name","email":"your.email@example.com"},"license":"MIT","_id":"ai-vision-mcp@0.0.4-beta","maintainers":[{"name":"tan-yong-sheng","email":"tys203831@gmail.com"}],"homepage":"https://github.com/tan-yong-sheng/ai-vision-mcp#readme","bugs":{"url":"https://github.com/tan-yong-sheng/ai-vision-mcp/issues"},"bin":{"ai-vision-mcp":"dist/index.js"},"dist":{"shasum":"bff1bd7a48dddce815711ea6ad266d7792fb2b7c","tarball":"https://registry.npmjs.org/ai-vision-mcp/-/ai-vision-mcp-0.0.4-beta.tgz","fileCount":143,"integrity":"sha512-WkbsN/0kZ6q5AXuNON5uQDYwxaeJLgOmb+8KZ9Mq61AwcsI/hBicqA7fo8kZfvMYgsWdWq+Z5QNGwu5AxyW5gw==","signatures":[{"sig":"MEUCIQCw2vIWZdjkklRYTaaxqscaUSNAiPgAJxFMwgm8AVWH/gIgVbU1PPjyQjA+6yd1gDj7bNZbT6qNqNeec0T4mjA9GjY=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":443187},"main":"dist/index.js","type":"module","types":"./dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"147497427fcc3f528cbcf826ea6e551359652cba","scripts":{"dev":"tsc --watch","lint":"eslint src/**/*.ts","build":"tsc","start":"node dist/index.js","format":"prettier --write src/**/*.ts","prepare":"npm run build","version":"npm run format && git add -A src","lint:fix":"eslint src/**/*.ts --fix","preversion":"npm run lint","postversion":"git push && git push --tags","prepublishOnly":"npm run lint","validate-server":"ajv validate -s https://registry.modelcontextprotocol.org/schemas/server-schema.json -d server.json","publish-registry":"mcp-publisher publish","publish-registry:dry-run":"mcp-publisher publish --dry-run"},"_npmUser":{"name":"tan-yong-sheng","email":"tys203831@gmail.com"},"repository":{"url":"git+https://github.com/tan-yong-sheng/ai-vision-mcp.git","type":"git"},"_npmVersion":"10.9.3","description":"Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI","directories":{},"_nodeVersion":"22.19.0","dependencies":{"zod":"^3.23.8","sharp":"^0.33.5","dotenv":"^16.4.5","mime-types":"^2.1.35","node-fetch":"^3.3.2","@google/genai":"^1.24.0","@aws-sdk/client-s3":"^3.901.0","@google-cloud/storage":"^7.17.1","@modelcontextprotocol/sdk":"^1.0.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"readmeFilename":"README.md","devDependencies":{"eslint":"^8.57.0","ajv-cli":"^5.0.0","prettier":"^3.3.2","@types/ws":"^8.18.1","typescript":"^5.5.0","@types/glob":"^8.1.0","@types/long":"^4.0.2","@types/node":"^20.14.0","@types/yauzl":"^2.10.3","@types/phoenix":"^1.6.6","@types/mime-types":"^2.1.4","@types/html-to-text":"^9.0.4","eslint-config-prettier":"^9.1.2","eslint-plugin-prettier":"^5.5.4","@typescript-eslint/parser":"^7.18.0","@types/http-cache-semantics":"^4.0.4","@typescript-eslint/eslint-plugin":"^7.18.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-vision-mcp_0.0.4-beta_1760157794583_0.663997235428031","host":"s3://npm-registry-packages-npm-production"}},"0.0.5":{"name":"ai-vision-mcp","version":"0.0.5","keywords":["mcp","vision","ai","image-analysis","video-analysis","gemini","vertex-ai","google-ai"],"author":{"name":"Your Name","email":"your.email@example.com"},"license":"MIT","_id":"ai-vision-mcp@0.0.5","maintainers":[{"name":"tan-yong-sheng","email":"tys203831@gmail.com"}],"homepage":"https://github.com/tan-yong-sheng/ai-vision-mcp#readme","bugs":{"url":"https://github.com/tan-yong-sheng/ai-vision-mcp/issues"},"bin":{"ai-vision-mcp":"dist/index.js"},"dist":{"shasum":"82ae43b99b3c662c1749a423b48cb84d81c702cc","tarball":"https://registry.npmjs.org/ai-vision-mcp/-/ai-vision-mcp-0.0.5.tgz","fileCount":143,"integrity":"sha512-4duCVlUm5bFdCLqX/L2/DNgAfftJUM63LNZ+/ulyERvY1DFCMrutDzbJBF9PDjvXYY67vjmuJAV4dZasP7k6DQ==","signatures":[{"sig":"MEUCIB2UBQT4HmFOvG1boh2xbBaz5Xt6h8gk3JQY2+u7Y6ajAiEA5WaBj++x1qwDEHiFacAFkaS6W+ct99Lbja1pSFwz7rA=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":443027},"main":"dist/index.js","type":"module","types":"./dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"91bd062eb8febf912cd96b04ea59c1038e36f356","scripts":{"dev":"tsc --watch","lint":"eslint src/**/*.ts","build":"tsc","start":"node dist/index.js","format":"prettier --write src/**/*.ts","prepare":"npm run build","version":"npm run format && git add -A src","lint:fix":"eslint src/**/*.ts --fix","preversion":"npm run lint","postversion":"git push && git push --tags","prepublishOnly":"npm run lint","publish-registry":"mcp-publisher publish","publish-registry:dry-run":"mcp-publisher publish --dry-run"},"_npmUser":{"name":"tan-yong-sheng","email":"tys203831@gmail.com"},"repository":{"url":"git+https://github.com/tan-yong-sheng/ai-vision-mcp.git","type":"git"},"_npmVersion":"10.9.3","description":"Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI","directories":{},"_nodeVersion":"22.19.0","dependencies":{"zod":"^3.23.8","sharp":"^0.33.5","dotenv":"^16.4.5","mime-types":"^2.1.35","node-fetch":"^3.3.2","@google/genai":"^1.24.0","@aws-sdk/client-s3":"^3.901.0","@google-cloud/storage":"^7.17.1","@modelcontextprotocol/sdk":"^1.0.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"eslint":"^8.57.0","prettier":"^3.3.2","@types/ws":"^8.18.1","typescript":"^5.5.0","@types/glob":"^8.1.0","@types/long":"^4.0.2","@types/node":"^20.14.0","@types/yauzl":"^2.10.3","@types/phoenix":"^1.6.6","@types/mime-types":"^2.1.4","@types/html-to-text":"^9.0.4","eslint-config-prettier":"^9.1.2","eslint-plugin-prettier":"^5.5.4","@typescript-eslint/parser":"^7.18.0","@types/http-cache-semantics":"^4.0.4","@typescript-eslint/eslint-plugin":"^7.18.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-vision-mcp_0.0.5_1760158590719_0.4057622290058853","host":"s3://npm-registry-packages-npm-production"}},"0.0.5-dev.20260211.411de3c":{"name":"ai-vision-mcp","version":"0.0.5-dev.20260211.411de3c","keywords":["mcp","vision","ai","image-analysis","video-analysis","gemini","vertex-ai","google-ai"],"author":{"name":"Tan Yong Sheng","email":"tys203831@gmail.com"},"license":"MIT","_id":"ai-vision-mcp@0.0.5-dev.20260211.411de3c","maintainers":[{"name":"tan-yong-sheng","email":"tys203831@gmail.com"}],"homepage":"https://github.com/tan-yong-sheng/ai-vision-mcp#readme","bugs":{"url":"https://github.com/tan-yong-sheng/ai-vision-mcp/issues"},"bin":{"ai-vision-mcp":"dist/index.js"},"dist":{"shasum":"93c43cba1158bd6a2e95c6f1e3db5883c83826f9","tarball":"https://registry.npmjs.org/ai-vision-mcp/-/ai-vision-mcp-0.0.5-dev.20260211.411de3c.tgz","fileCount":143,"integrity":"sha512-gSRm9B1s9xgQzoeTEdI8xUNp8CaBMtX3+pHLbIjTMzf/kwRiLeDAduDBBpQtw29E3pJqmkXtpP3Er+KK0UBqLQ==","signatures":[{"sig":"MEYCIQCZH8I7KIhwaM9yUmZ7H2nP3jov7X+s1nDbiHIcGpFW/gIhALkV2DY1V2xRXcNTSMEonG/t6GrC+P8U4W+KyIvux/xZ","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/ai-vision-mcp@0.0.5-dev.20260211.411de3c","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":436686},"main":"dist/index.js","type":"module","types":"./dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"411de3caab82e92720ac0f9b3a7fddb140058bd0","scripts":{"dev":"tsc --watch","lint":"eslint src/**/*.ts","build":"tsc","start":"node dist/index.js","format":"prettier --write src/**/*.ts","prepare":"npm run build","version":"npm run format && git add -A src","lint:fix":"eslint src/**/*.ts --fix","preversion":"npm run lint","postversion":"git push && git push --tags","prepublishOnly":"npm run lint","publish-registry":"mcp-publisher publish","publish-registry:dry-run":"mcp-publisher publish --dry-run"},"_npmUser":{"name":"tan-yong-sheng","email":"tys203831@gmail.com"},"repository":{"url":"git+https://github.com/tan-yong-sheng/ai-vision-mcp.git","type":"git"},"_npmVersion":"10.8.2","description":"Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI","directories":{},"_nodeVersion":"20.20.0","dependencies":{"zod":"^3.23.8","sharp":"^0.33.5","dotenv":"^16.4.5","mime-types":"^2.1.35","node-fetch":"^3.3.2","@google/genai":"^1.24.0","@google-cloud/storage":"^7.17.1","@modelcontextprotocol/sdk":"^1.0.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"readmeFilename":"README.md","devDependencies":{"eslint":"^8.57.0","prettier":"^3.3.2","@types/ws":"^8.18.1","typescript":"^5.5.0","@types/glob":"^8.1.0","@types/long":"^4.0.2","@types/node":"^20.14.0","@types/yauzl":"^2.10.3","@types/phoenix":"^1.6.6","@types/mime-types":"^2.1.4","@types/html-to-text":"^9.0.4","eslint-config-prettier":"^9.1.2","eslint-plugin-prettier":"^5.5.4","@typescript-eslint/parser":"^7.18.0","@types/http-cache-semantics":"^4.0.4","@typescript-eslint/eslint-plugin":"^7.18.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-vision-mcp_0.0.5-dev.20260211.411de3c_1770792185658_0.41369215840526063","host":"s3://npm-registry-packages-npm-production"}},"0.0.5-dev.20260211.3638630":{"name":"ai-vision-mcp","version":"0.0.5-dev.20260211.3638630","keywords":["mcp","vision","ai","image-analysis","video-analysis","gemini","vertex-ai","google-ai"],"author":{"name":"Tan Yong Sheng","email":"tys203831@gmail.com"},"license":"MIT","_id":"ai-vision-mcp@0.0.5-dev.20260211.3638630","maintainers":[{"name":"tan-yong-sheng","email":"tys203831@gmail.com"}],"homepage":"https://github.com/tan-yong-sheng/ai-vision-mcp#readme","bugs":{"url":"https://github.com/tan-yong-sheng/ai-vision-mcp/issues"},"bin":{"ai-vision-mcp":"dist/index.js"},"dist":{"shasum":"ac27a00f4ff0838e99e76303fce044dd84b03250","tarball":"https://registry.npmjs.org/ai-vision-mcp/-/ai-vision-mcp-0.0.5-dev.20260211.3638630.tgz","fileCount":143,"integrity":"sha512-KSCs5ZAyjsVMPpiCZOUx9MyUgPbjc9S2ZozcE8xyoE+7nEo158NJ/USXS5qIyqRtwAIaTvvxIOdYgwFWo8ikoQ==","signatures":[{"sig":"MEYCIQCGgPvbSvI8eMsMS9JJIE0674Lixt8r0h2Dh13lRT4e3AIhAK3CTLTXV+ZfJnzh8Y9yJ6tblQuoTx0uj+B+Aih6SaT+","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/ai-vision-mcp@0.0.5-dev.20260211.3638630","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":436686},"main":"dist/index.js","type":"module","types":"./dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"3638630185e993867852376ed4c2b8f68bc95548","scripts":{"dev":"tsc --watch","lint":"eslint src/**/*.ts","build":"tsc","start":"node dist/index.js","format":"prettier --write src/**/*.ts","prepare":"npm run build","version":"npm run format && git add -A src","lint:fix":"eslint src/**/*.ts --fix","preversion":"npm run lint","postversion":"git push && git push --tags","prepublishOnly":"npm run lint","publish-registry":"mcp-publisher publish","publish-registry:dry-run":"mcp-publisher publish --dry-run"},"_npmUser":{"name":"tan-yong-sheng","email":"tys203831@gmail.com"},"repository":{"url":"git+https://github.com/tan-yong-sheng/ai-vision-mcp.git","type":"git"},"_npmVersion":"10.8.2","description":"Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI","directories":{},"_nodeVersion":"20.20.0","dependencies":{"zod":"^3.23.8","sharp":"^0.33.5","dotenv":"^16.4.5","mime-types":"^2.1.35","node-fetch":"^3.3.2","@google/genai":"^1.24.0","@google-cloud/storage":"^7.17.1","@modelcontextprotocol/sdk":"^1.0.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"readmeFilename":"README.md","devDependencies":{"eslint":"^8.57.0","prettier":"^3.3.2","@types/ws":"^8.18.1","typescript":"^5.5.0","@types/glob":"^8.1.0","@types/long":"^4.0.2","@types/node":"^20.14.0","@types/yauzl":"^2.10.3","@types/phoenix":"^1.6.6","@types/mime-types":"^2.1.4","@types/html-to-text":"^9.0.4","eslint-config-prettier":"^9.1.2","eslint-plugin-prettier":"^5.5.4","@typescript-eslint/parser":"^7.18.0","@types/http-cache-semantics":"^4.0.4","@typescript-eslint/eslint-plugin":"^7.18.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-vision-mcp_0.0.5-dev.20260211.3638630_1770793521232_0.8093406089602186","host":"s3://npm-registry-packages-npm-production"}},"0.0.5-dev.20260211.335468b":{"name":"ai-vision-mcp","version":"0.0.5-dev.20260211.335468b","keywords":["mcp","vision","ai","image-analysis","video-analysis","gemini","vertex-ai","google-ai"],"author":{"name":"Tan Yong Sheng","email":"tys203831@gmail.com"},"license":"MIT","_id":"ai-vision-mcp@0.0.5-dev.20260211.335468b","maintainers":[{"name":"tan-yong-sheng","email":"tys203831@gmail.com"}],"homepage":"https://github.com/tan-yong-sheng/ai-vision-mcp#readme","bugs":{"url":"https://github.com/tan-yong-sheng/ai-vision-mcp/issues"},"bin":{"ai-vision-mcp":"dist/index.js"},"dist":{"shasum":"6c8328e8112e4cd5f39b8d610da43fecf95f5c13","tarball":"https://registry.npmjs.org/ai-vision-mcp/-/ai-vision-mcp-0.0.5-dev.20260211.335468b.tgz","fileCount":143,"integrity":"sha512-SSa4dxxCkyMJqTNrbpieEYkdW42oZ+E+qaIO3l0IITuRyNKQ+d/iqS/uzQhmjZjLt3j/BlMs7PmbNlQ/Z0nLsA==","signatures":[{"sig":"MEUCIQCtz47+1tuG0OiGU3QUH0XX+7z2i+xos+lQYls6LrBz+QIgGm9Hzxg9WmNsK2KESyaa8OwJ5BZEbH13S5N6Mf/YIMA=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/ai-vision-mcp@0.0.5-dev.20260211.335468b","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":436686},"main":"dist/index.js","type":"module","types":"./dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"335468bba2ee73411bf3ace6164e741e7662af13","scripts":{"dev":"tsc --watch","lint":"eslint src/**/*.ts","build":"tsc","start":"node dist/index.js","format":"prettier --write src/**/*.ts","prepare":"npm run build","version":"npm run format && git add -A src","lint:fix":"eslint src/**/*.ts --fix","preversion":"npm run lint","postversion":"git push && git push --tags","prepublishOnly":"npm run lint","publish-registry":"mcp-publisher publish","publish-registry:dry-run":"mcp-publisher publish --dry-run"},"_npmUser":{"name":"tan-yong-sheng","email":"tys203831@gmail.com"},"repository":{"url":"git+https://github.com/tan-yong-sheng/ai-vision-mcp.git","type":"git"},"_npmVersion":"10.8.2","description":"Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI","directories":{},"_nodeVersion":"20.20.0","dependencies":{"zod":"^3.23.8","sharp":"^0.33.5","dotenv":"^16.4.5","mime-types":"^2.1.35","node-fetch":"^3.3.2","@google/genai":"^1.24.0","@google-cloud/storage":"^7.17.1","@modelcontextprotocol/sdk":"^1.0.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"readmeFilename":"README.md","devDependencies":{"eslint":"^8.57.0","prettier":"^3.3.2","@types/ws":"^8.18.1","typescript":"^5.5.0","@types/glob":"^8.1.0","@types/long":"^4.0.2","@types/node":"^20.14.0","@types/yauzl":"^2.10.3","@types/phoenix":"^1.6.6","@types/mime-types":"^2.1.4","@types/html-to-text":"^9.0.4","eslint-config-prettier":"^9.1.2","eslint-plugin-prettier":"^5.5.4","@typescript-eslint/parser":"^7.18.0","@types/http-cache-semantics":"^4.0.4","@typescript-eslint/eslint-plugin":"^7.18.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-vision-mcp_0.0.5-dev.20260211.335468b_1770793650139_0.9850949455176266","host":"s3://npm-registry-packages-npm-production"}},"0.0.5-dev.20260211.6cf3ff2":{"name":"ai-vision-mcp","version":"0.0.5-dev.20260211.6cf3ff2","keywords":["mcp","vision","ai","image-analysis","video-analysis","gemini","vertex-ai","google-ai"],"author":{"name":"Tan Yong Sheng","email":"tys203831@gmail.com"},"license":"MIT","_id":"ai-vision-mcp@0.0.5-dev.20260211.6cf3ff2","maintainers":[{"name":"tan-yong-sheng","email":"tys203831@gmail.com"}],"homepage":"https://github.com/tan-yong-sheng/ai-vision-mcp#readme","bugs":{"url":"https://github.com/tan-yong-sheng/ai-vision-mcp/issues"},"bin":{"ai-vision-mcp":"dist/index.js"},"dist":{"shasum":"23b7dd02f0443c8644f2c9215ddb775ce9258da7","tarball":"https://registry.npmjs.org/ai-vision-mcp/-/ai-vision-mcp-0.0.5-dev.20260211.6cf3ff2.tgz","fileCount":147,"integrity":"sha512-e/nhnI/9GnrJ1k8cpzMpe5zU+rt152jfoh7I0eK9+tCnKBfrVDMJpvD0cVbw1KeRRtBcY25Vn+PXx8XRUWBPvA==","signatures":[{"sig":"MEUCIEZlIVGflGSiC/Ylzu9UVztctQpi2TcyylER6FXvr/2VAiEA9JYi/6vd5xFnKWrM5bcJx4Yu8EYB91Ib5hIZ8w0fJwc=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/ai-vision-mcp@0.0.5-dev.20260211.6cf3ff2","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":451924},"main":"dist/index.js","type":"module","types":"./dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"6cf3ff21cdb178d4e2a78478a791969e79b11677","scripts":{"dev":"tsc --watch","lint":"eslint src/**/*.ts","build":"tsc","start":"node dist/index.js","doctor":"npm run check:imagescript","format":"prettier --write src/**/*.ts","prepare":"npm run build","version":"npm run format && git add -A src","lint:fix":"eslint src/**/*.ts --fix","preversion":"npm run lint","postversion":"git push && git push --tags","prepublishOnly":"npm run lint","publish-registry":"mcp-publisher publish","check:imagescript":"node -e \"import('imagescript').then(()=>console.error('imagescript:ok')).catch(e=>{console.error('imagescript:fail'); console.error(e&&e.message||e); process.exit(1);})\"","publish-registry:dry-run":"mcp-publisher publish --dry-run"},"_npmUser":{"name":"tan-yong-sheng","email":"tys203831@gmail.com"},"repository":{"url":"git+https://github.com/tan-yong-sheng/ai-vision-mcp.git","type":"git"},"_npmVersion":"10.8.2","description":"Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI","directories":{},"_nodeVersion":"20.20.0","dependencies":{"zod":"^3.23.8","dotenv":"^16.4.5","mime-types":"^2.1.35","node-fetch":"^3.3.2","imagescript":"^1.3.0","@google/genai":"^1.24.0","@google-cloud/storage":"^7.19.0","@modelcontextprotocol/sdk":"^1.26.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"readmeFilename":"README.md","devDependencies":{"eslint":"^8.57.0","prettier":"^3.3.2","@types/ws":"^8.18.1","typescript":"^5.5.0","@types/node":"^20.14.0","@types/yauzl":"^2.10.3","@types/phoenix":"^1.6.6","@types/mime-types":"^2.1.4","@types/html-to-text":"^9.0.4","eslint-config-prettier":"^9.1.2","eslint-plugin-prettier":"^5.5.4","@typescript-eslint/parser":"^7.18.0","@types/http-cache-semantics":"^4.0.4","@typescript-eslint/eslint-plugin":"^7.18.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-vision-mcp_0.0.5-dev.20260211.6cf3ff2_1770794353333_0.5571980644549586","host":"s3://npm-registry-packages-npm-production"}},"0.0.5-dev.20260211.a510d24":{"name":"ai-vision-mcp","version":"0.0.5-dev.20260211.a510d24","keywords":["mcp","vision","ai","image-analysis","video-analysis","gemini","vertex-ai","google-ai"],"author":{"name":"Tan Yong Sheng","email":"tys203831@gmail.com"},"license":"MIT","_id":"ai-vision-mcp@0.0.5-dev.20260211.a510d24","maintainers":[{"name":"tan-yong-sheng","email":"tys203831@gmail.com"}],"homepage":"https://github.com/tan-yong-sheng/ai-vision-mcp#readme","bugs":{"url":"https://github.com/tan-yong-sheng/ai-vision-mcp/issues"},"bin":{"ai-vision":"dist/index.js","ai-vision-mcp":"dist/index.js"},"dist":{"shasum":"cdebab3f269cee030a522425ff5f00ddfddd9db2","tarball":"https://registry.npmjs.org/ai-vision-mcp/-/ai-vision-mcp-0.0.5-dev.20260211.a510d24.tgz","fileCount":171,"integrity":"sha512-Ar1UvQmhOA85SInjyv1Zsyy2DJFX7HvolBEzKDqapEZS4Jp1U/Rt4ErvIc/Qq4fohDEcCrGKGjEClIaYjeAhpg==","signatures":[{"sig":"MEUCIQCLt6Q5sDcfP4mM4DPT198E7ScTpMnDoBcI43Vh8RV3WwIgb6bM+lbZ+Qr50h+w0aZA1ZcpuUOtvYdKq+65rk3MJH0=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/ai-vision-mcp@0.0.5-dev.20260211.a510d24","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":476881},"main":"dist/index.js","type":"module","types":"./dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"a510d24992cb357d0257df81c37059dfce77f4a9","scripts":{"dev":"tsc --watch","lint":"eslint src/**/*.ts","test":"vitest run","build":"tsc","start":"node dist/index.js","doctor":"npm run check:imagescript","format":"prettier --write src/**/*.ts","prepare":"npm run build","version":"npm run format && git add -A src","lint:fix":"eslint src/**/*.ts --fix","test:e2e":"vitest run tests/e2e","preversion":"npm run lint","test:watch":"vitest watch","postversion":"git push && git push --tags","test:e2e:ci":"vitest run tests/e2e/protocol.test.ts tests/e2e/validation.test.ts","test:e2e:cli":"vitest run tests/e2e/cli.test.ts","prepublishOnly":"npm run lint","publish-registry":"mcp-publisher publish","check:imagescript":"node -e \"import('imagescript').then(()=>console.error('imagescript:ok')).catch(e=>{console.error('imagescript:fail'); console.error(e&&e.message||e); process.exit(1);})\"","test:e2e:protocol":"vitest run tests/e2e/protocol.test.ts","publish-registry:dry-run":"mcp-publisher publish --dry-run"},"_npmUser":{"name":"tan-yong-sheng","email":"tys203831@gmail.com"},"repository":{"url":"git+https://github.com/tan-yong-sheng/ai-vision-mcp.git","type":"git"},"_npmVersion":"10.8.2","description":"Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI","directories":{},"_nodeVersion":"20.20.0","dependencies":{"zod":"^3.23.8","dotenv":"^16.4.5","mime-types":"^2.1.35","node-fetch":"^3.3.2","imagescript":"^1.3.0","@google/genai":"^1.24.0","@google-cloud/storage":"^7.19.0","@modelcontextprotocol/sdk":"^1.26.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"readmeFilename":"README.md","devDependencies":{"knip":"^5.83.1","eslint":"^8.57.0","vitest":"^4.0.18","depcheck":"^1.4.7","prettier":"^3.3.2","ts-prune":"^0.10.3","@types/ws":"^8.18.1","typescript":"^5.5.0","@types/node":"^20.14.0","@types/yauzl":"^2.10.3","@types/phoenix":"^1.6.6","@types/mime-types":"^2.1.4","@types/html-to-text":"^9.0.4","@vitest/coverage-v8":"^4.0.18","eslint-config-prettier":"^9.1.2","eslint-plugin-prettier":"^5.5.4","@typescript-eslint/parser":"^7.18.0","@types/http-cache-semantics":"^4.0.4","@typescript-eslint/eslint-plugin":"^7.18.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-vision-mcp_0.0.5-dev.20260211.a510d24_1770814197856_0.6301560399886281","host":"s3://npm-registry-packages-npm-production"}},"0.0.5-dev.20260211.5498e54":{"name":"ai-vision-mcp","version":"0.0.5-dev.20260211.5498e54","keywords":["mcp","vision","ai","image-analysis","video-analysis","gemini","vertex-ai","google-ai"],"author":{"name":"Tan Yong Sheng","email":"tys203831@gmail.com"},"license":"MIT","_id":"ai-vision-mcp@0.0.5-dev.20260211.5498e54","maintainers":[{"name":"tan-yong-sheng","email":"tys203831@gmail.com"}],"homepage":"https://github.com/tan-yong-sheng/ai-vision-mcp#readme","bugs":{"url":"https://github.com/tan-yong-sheng/ai-vision-mcp/issues"},"bin":{"ai-vision":"dist/index.js","ai-vision-mcp":"dist/index.js"},"dist":{"shasum":"0a5ef9bd34492cfd16208b1576e4f5d0388b6869","tarball":"https://registry.npmjs.org/ai-vision-mcp/-/ai-vision-mcp-0.0.5-dev.20260211.5498e54.tgz","fileCount":171,"integrity":"sha512-LPnJsNpooYWXKvlA2R4sDKcRW8KMLLSR3XF9U4T7r/gNkEo4JiYnvSP4jz8yYWZaZn8dl7ENcL5Oyi2s7fYtTg==","signatures":[{"sig":"MEUCIQCWqFPQRFZCCEcLSk0iyh0SeW7D91UhadMuGlbAEa3fKgIgPkHkWSFqIaMOB9ZZow87p18z5DqkA2Uz3DZNUh7mwVk=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/ai-vision-mcp@0.0.5-dev.20260211.5498e54","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":476881},"main":"dist/index.js","type":"module","types":"./dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"5498e54c866fdbdae28dd1c65ca00b57ad55c4d0","scripts":{"dev":"tsc --watch","lint":"eslint src/**/*.ts","test":"vitest run","build":"tsc","start":"node dist/index.js","doctor":"npm run check:imagescript","format":"prettier --write src/**/*.ts","prepare":"npm run build","version":"npm run format && git add -A src","lint:fix":"eslint src/**/*.ts --fix","test:e2e":"vitest run tests/e2e","preversion":"npm run lint","test:watch":"vitest watch","postversion":"git push && git push --tags","test:e2e:ci":"vitest run tests/e2e/protocol.test.ts tests/e2e/validation.test.ts","test:e2e:cli":"vitest run tests/e2e/cli.test.ts","prepublishOnly":"npm run lint","publish-registry":"mcp-publisher publish","check:imagescript":"node -e \"import('imagescript').then(()=>console.error('imagescript:ok')).catch(e=>{console.error('imagescript:fail'); console.error(e&&e.message||e); process.exit(1);})\"","test:e2e:protocol":"vitest run tests/e2e/protocol.test.ts","publish-registry:dry-run":"mcp-publisher publish --dry-run"},"_npmUser":{"name":"tan-yong-sheng","email":"tys203831@gmail.com"},"repository":{"url":"git+https://github.com/tan-yong-sheng/ai-vision-mcp.git","type":"git"},"_npmVersion":"10.8.2","description":"Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI","directories":{},"_nodeVersion":"20.20.0","dependencies":{"zod":"^3.23.8","dotenv":"^16.4.5","mime-types":"^2.1.35","node-fetch":"^3.3.2","imagescript":"^1.3.0","@google/genai":"^1.24.0","@google-cloud/storage":"^7.19.0","@modelcontextprotocol/sdk":"^1.26.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"readmeFilename":"README.md","devDependencies":{"knip":"^5.83.1","eslint":"^8.57.0","vitest":"^4.0.18","depcheck":"^1.4.7","prettier":"^3.3.2","ts-prune":"^0.10.3","@types/ws":"^8.18.1","typescript":"^5.5.0","@types/node":"^20.14.0","@types/yauzl":"^2.10.3","@types/phoenix":"^1.6.6","@types/mime-types":"^2.1.4","@types/html-to-text":"^9.0.4","@vitest/coverage-v8":"^4.0.18","eslint-config-prettier":"^9.1.2","eslint-plugin-prettier":"^5.5.4","@typescript-eslint/parser":"^7.18.0","@types/http-cache-semantics":"^4.0.4","@typescript-eslint/eslint-plugin":"^7.18.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-vision-mcp_0.0.5-dev.20260211.5498e54_1770814450120_0.1870723876649567","host":"s3://npm-registry-packages-npm-production"}},"0.0.5-dev.20260211.d766dc0":{"name":"ai-vision-mcp","version":"0.0.5-dev.20260211.d766dc0","keywords":["mcp","vision","ai","image-analysis","video-analysis","gemini","vertex-ai","google-ai"],"author":{"name":"Tan Yong Sheng","email":"tys203831@gmail.com"},"license":"MIT","_id":"ai-vision-mcp@0.0.5-dev.20260211.d766dc0","maintainers":[{"name":"tan-yong-sheng","email":"tys203831@gmail.com"}],"homepage":"https://github.com/tan-yong-sheng/ai-vision-mcp#readme","bugs":{"url":"https://github.com/tan-yong-sheng/ai-vision-mcp/issues"},"bin":{"ai-vision":"dist/index.js","ai-vision-mcp":"dist/index.js"},"dist":{"shasum":"fd8b05f3234d9e2cd5ec3c13c393c9fabd3f718a","tarball":"https://registry.npmjs.org/ai-vision-mcp/-/ai-vision-mcp-0.0.5-dev.20260211.d766dc0.tgz","fileCount":171,"integrity":"sha512-kOXiVAOFTIAeP3TviOZgaxkIBsLfniRcqLppj+7bnpGgRxseh8844pBkMMhsqY80Tuf5qan1+7QU/WeEsvhPwg==","signatures":[{"sig":"MEUCIQDFZef6S8oYS5ApXAGl0Vs6XGkFtfYdp0U6qutJPhtV7wIgWRJ90bCJiBablCv7PXX8AFAK/NnJVTuqiFqBg5Kj4sc=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/ai-vision-mcp@0.0.5-dev.20260211.d766dc0","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":478079},"main":"dist/index.js","type":"module","types":"./dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"d766dc01a8670eb141cbccff98004487f9f751de","scripts":{"dev":"tsc --watch","lint":"eslint src/**/*.ts","test":"vitest run","build":"tsc","start":"node dist/index.js","doctor":"npm run check:imagescript","format":"prettier --write src/**/*.ts","prepare":"npm run build","version":"npm run format && git add -A src","lint:fix":"eslint src/**/*.ts --fix","test:e2e":"vitest run tests/e2e","preversion":"npm run lint","test:watch":"vitest watch","postversion":"git push && git push --tags","test:e2e:ci":"vitest run tests/e2e/protocol.test.ts tests/e2e/validation.test.ts","test:e2e:cli":"vitest run tests/e2e/cli.test.ts","prepublishOnly":"npm run lint","publish-registry":"mcp-publisher publish","check:imagescript":"node -e \"import('imagescript').then(()=>console.error('imagescript:ok')).catch(e=>{console.error('imagescript:fail'); console.error(e&&e.message||e); process.exit(1);})\"","test:e2e:protocol":"vitest run tests/e2e/protocol.test.ts","publish-registry:dry-run":"mcp-publisher publish --dry-run"},"_npmUser":{"name":"tan-yong-sheng","email":"tys203831@gmail.com"},"repository":{"url":"git+https://github.com/tan-yong-sheng/ai-vision-mcp.git","type":"git"},"_npmVersion":"10.8.2","description":"Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI","directories":{},"_nodeVersion":"20.20.0","dependencies":{"zod":"^3.23.8","dotenv":"^16.4.5","mime-types":"^2.1.35","node-fetch":"^3.3.2","imagescript":"^1.3.0","@google/genai":"^1.24.0","@google-cloud/storage":"^7.19.0","@modelcontextprotocol/sdk":"^1.26.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"readmeFilename":"README.md","devDependencies":{"knip":"^5.83.1","eslint":"^8.57.0","vitest":"^4.0.18","depcheck":"^1.4.7","prettier":"^3.3.2","ts-prune":"^0.10.3","@types/ws":"^8.18.1","typescript":"^5.5.0","@types/node":"^20.14.0","@types/yauzl":"^2.10.3","@types/phoenix":"^1.6.6","@types/mime-types":"^2.1.4","@types/html-to-text":"^9.0.4","@vitest/coverage-v8":"^4.0.18","eslint-config-prettier":"^9.1.2","eslint-plugin-prettier":"^5.5.4","@typescript-eslint/parser":"^7.18.0","@types/http-cache-semantics":"^4.0.4","@typescript-eslint/eslint-plugin":"^7.18.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-vision-mcp_0.0.5-dev.20260211.d766dc0_1770816340424_0.030927307710878926","host":"s3://npm-registry-packages-npm-production"}},"0.0.5-dev.20260211.7addf1a":{"name":"ai-vision-mcp","version":"0.0.5-dev.20260211.7addf1a","keywords":["mcp","vision","ai","image-analysis","video-analysis","gemini","vertex-ai","google-ai"],"author":{"name":"Tan Yong Sheng","email":"tys203831@gmail.com"},"license":"MIT","_id":"ai-vision-mcp@0.0.5-dev.20260211.7addf1a","maintainers":[{"name":"tan-yong-sheng","email":"tys203831@gmail.com"}],"homepage":"https://github.com/tan-yong-sheng/ai-vision-mcp#readme","bugs":{"url":"https://github.com/tan-yong-sheng/ai-vision-mcp/issues"},"bin":{"ai-vision":"dist/index.js","ai-vision-mcp":"dist/index.js"},"dist":{"shasum":"49e4af1c1fe945f468629f53cbd2aa467e1a173e","tarball":"https://registry.npmjs.org/ai-vision-mcp/-/ai-vision-mcp-0.0.5-dev.20260211.7addf1a.tgz","fileCount":171,"integrity":"sha512-2z6sLYRQjRwlkzIFjT3Wtot7talrKdWt7K3nre7xiJKstzqBE/yCtTBkLq05qOz0yGCvoPjJjl6k6SVAkaNphQ==","signatures":[{"sig":"MEUCIF3EefoF/ZqdKq1P1b9uAWpoUV3gZoiabbIJjoN+EwyIAiEAtLFBPSyu1i/S+jUanmkTFW8MIgEgAV0cnMwBRWhN+qU=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/ai-vision-mcp@0.0.5-dev.20260211.7addf1a","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":480136},"main":"dist/index.js","type":"module","types":"./dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"7addf1afcd0943d362295879b3f8c38665c890ce","scripts":{"dev":"tsc --watch","lint":"eslint src/**/*.ts","test":"vitest run","build":"tsc","start":"node dist/index.js","doctor":"npm run check:imagescript","format":"prettier --write src/**/*.ts","prepare":"npm run build","version":"npm run format && git add -A src","lint:fix":"eslint src/**/*.ts --fix","test:e2e":"vitest run tests/e2e","preversion":"npm run lint","test:watch":"vitest watch","postversion":"git push && git push --tags","test:e2e:ci":"vitest run tests/e2e/protocol.test.ts tests/e2e/validation.test.ts","test:e2e:cli":"vitest run tests/e2e/cli.test.ts","prepublishOnly":"npm run lint","publish-registry":"mcp-publisher publish","check:imagescript":"node -e \"import('imagescript').then(()=>console.error('imagescript:ok')).catch(e=>{console.error('imagescript:fail'); console.error(e&&e.message||e); process.exit(1);})\"","test:e2e:protocol":"vitest run tests/e2e/protocol.test.ts","publish-registry:dry-run":"mcp-publisher publish --dry-run"},"_npmUser":{"name":"tan-yong-sheng","email":"tys203831@gmail.com"},"repository":{"url":"git+https://github.com/tan-yong-sheng/ai-vision-mcp.git","type":"git"},"_npmVersion":"10.8.2","description":"Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI","directories":{},"_nodeVersion":"20.20.0","dependencies":{"zod":"^3.23.8","dotenv":"^16.4.5","mime-types":"^2.1.35","node-fetch":"^3.3.2","imagescript":"^1.3.0","@google/genai":"^1.24.0","@google-cloud/storage":"^7.19.0","@modelcontextprotocol/sdk":"^1.26.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"readmeFilename":"README.md","devDependencies":{"knip":"^5.83.1","eslint":"^8.57.0","vitest":"^4.0.18","depcheck":"^1.4.7","prettier":"^3.3.2","ts-prune":"^0.10.3","@types/ws":"^8.18.1","typescript":"^5.5.0","@types/node":"^20.14.0","@types/yauzl":"^2.10.3","@types/phoenix":"^1.6.6","@types/mime-types":"^2.1.4","@types/html-to-text":"^9.0.4","@vitest/coverage-v8":"^4.0.18","eslint-config-prettier":"^9.1.2","eslint-plugin-prettier":"^5.5.4","@typescript-eslint/parser":"^7.18.0","@types/http-cache-semantics":"^4.0.4","@typescript-eslint/eslint-plugin":"^7.18.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-vision-mcp_0.0.5-dev.20260211.7addf1a_1770816748112_0.7292217718893557","host":"s3://npm-registry-packages-npm-production"}},"0.0.5-dev.1":{"name":"ai-vision-mcp","version":"0.0.5-dev.1","keywords":["mcp","vision","ai","image-analysis","video-analysis","gemini","vertex-ai","google-ai"],"author":{"name":"Tan Yong Sheng","email":"tys203831@gmail.com"},"license":"MIT","_id":"ai-vision-mcp@0.0.5-dev.1","maintainers":[{"name":"tan-yong-sheng","email":"tys203831@gmail.com"}],"homepage":"https://github.com/tan-yong-sheng/ai-vision-mcp#readme","bugs":{"url":"https://github.com/tan-yong-sheng/ai-vision-mcp/issues"},"bin":{"ai-vision":"dist/index.js","ai-vision-mcp":"dist/index.js"},"dist":{"shasum":"f8483ad486f47d54b18be87541a3c88255c34bfc","tarball":"https://registry.npmjs.org/ai-vision-mcp/-/ai-vision-mcp-0.0.5-dev.1.tgz","fileCount":171,"integrity":"sha512-htPOZACV5pekIxLuC6DqGlUUfuO1SynUjoZNTKI8EjcwPj8QU4jhYjgTx8AVzsHzx84WIttat9nEm1uEXTMcQA==","signatures":[{"sig":"MEQCIF/gokZywFFbgglh4mbPHA63HaN72290se+k0MwWd1pLAiB0p5IU8jwz4/FzBM/+/llKldSNVI2SEYGCdFiko2iH+w==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/ai-vision-mcp@0.0.5-dev.1","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":492008},"main":"dist/index.js","type":"module","types":"./dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"9f7cf904af07b5c0209c1ee72f475b6e3516e488","scripts":{"dev":"tsc --watch","lint":"eslint src/**/*.ts","test":"vitest run","build":"tsc","start":"node dist/index.js","doctor":"npm run check:imagescript","format":"prettier --write src/**/*.ts","prepare":"npm run build","version":"npm run format && git add -A src","lint:fix":"eslint src/**/*.ts --fix","test:e2e":"vitest run tests/e2e","preversion":"npm run lint","test:watch":"vitest watch","postversion":"git push && git push --tags","test:e2e:ci":"vitest run tests/e2e/protocol.test.ts tests/e2e/validation.test.ts","test:e2e:cli":"vitest run tests/e2e/cli.test.ts","prepublishOnly":"npm run lint","publish-registry":"mcp-publisher publish","check:imagescript":"node -e \"import('imagescript').then(()=>console.error('imagescript:ok')).catch(e=>{console.error('imagescript:fail'); console.error(e&&e.message||e); process.exit(1);})\"","test:e2e:protocol":"vitest run tests/e2e/protocol.test.ts","publish-registry:dry-run":"mcp-publisher publish --dry-run"},"_npmUser":{"name":"tan-yong-sheng","email":"tys203831@gmail.com"},"repository":{"url":"git+https://github.com/tan-yong-sheng/ai-vision-mcp.git","type":"git"},"_npmVersion":"10.8.2","description":"Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI","directories":{},"_nodeVersion":"20.20.0","dependencies":{"zod":"^3.23.8","dotenv":"^16.4.5","mime-types":"^2.1.35","node-fetch":"^3.3.2","imagescript":"^1.3.0","@google/genai":"^1.24.0","@google-cloud/storage":"^7.19.0","@modelcontextprotocol/sdk":"^1.26.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"readmeFilename":"README.md","devDependencies":{"knip":"^5.83.1","eslint":"^8.57.0","vitest":"^4.0.18","depcheck":"^1.4.7","prettier":"^3.3.2","ts-prune":"^0.10.3","@types/ws":"^8.18.1","typescript":"^5.5.0","@types/node":"^20.14.0","@types/yauzl":"^2.10.3","@types/phoenix":"^1.6.6","@types/mime-types":"^2.1.4","@types/html-to-text":"^9.0.4","@vitest/coverage-v8":"^4.0.18","eslint-config-prettier":"^9.1.2","eslint-plugin-prettier":"^5.5.4","@typescript-eslint/parser":"^7.18.0","@types/http-cache-semantics":"^4.0.4","@typescript-eslint/eslint-plugin":"^7.18.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-vision-mcp_0.0.5-dev.1_1770832093325_0.8851375827656436","host":"s3://npm-registry-packages-npm-production"}},"0.0.5-dev.2":{"name":"ai-vision-mcp","version":"0.0.5-dev.2","keywords":["mcp","vision","ai","image-analysis","video-analysis","gemini","vertex-ai","google-ai"],"author":{"name":"Tan Yong Sheng","email":"tys203831@gmail.com"},"license":"MIT","_id":"ai-vision-mcp@0.0.5-dev.2","maintainers":[{"name":"tan-yong-sheng","email":"tys203831@gmail.com"}],"homepage":"https://github.com/tan-yong-sheng/ai-vision-mcp#readme","bugs":{"url":"https://github.com/tan-yong-sheng/ai-vision-mcp/issues"},"bin":{"ai-vision":"dist/index.js","ai-vision-mcp":"dist/index.js"},"dist":{"shasum":"80fd0a5aee644f451011d8231abf1ffdcf949585","tarball":"https://registry.npmjs.org/ai-vision-mcp/-/ai-vision-mcp-0.0.5-dev.2.tgz","fileCount":183,"integrity":"sha512-qoBEr4T4jGeH877V01z1Ju/pbyv/oZgdFhsyoFzeIdkStLLUqEgZ+H9P9fB9P4mzz0uGh2FbHUpObLBU0gGzAQ==","signatures":[{"sig":"MEQCIEvij8vsXL5llEXNyxfQH4cKteSqloyNJ5spHyJxhDZXAiBUQyWyyWoVpM5A5WUmfGNSE6VKKUbYcqYGFfLeHaZ8gg==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/ai-vision-mcp@0.0.5-dev.2","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":525645},"main":"dist/index.js","type":"module","types":"./dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"19a40e610456b9c9c576affb26e05b351b7f8cfb","scripts":{"dev":"tsc --watch","lint":"eslint src/**/*.ts","test":"vitest run","build":"tsc","start":"node dist/index.js","doctor":"npm run check:imagescript","format":"prettier --write src/**/*.ts","prepare":"npm run build","version":"npm run format && git add -A src","lint:fix":"eslint src/**/*.ts --fix","test:e2e":"vitest run tests/e2e","preversion":"npm run lint","test:watch":"vitest watch","postversion":"git push && git push --tags","test:e2e:ci":"vitest run tests/e2e/protocol.test.ts tests/e2e/validation.test.ts","test:e2e:cli":"vitest run tests/e2e/cli.test.ts","prepublishOnly":"npm run lint","publish-registry":"mcp-publisher publish","check:imagescript":"node -e \"import('imagescript').then(()=>console.error('imagescript:ok')).catch(e=>{console.error('imagescript:fail'); console.error(e&&e.message||e); process.exit(1);})\"","test:e2e:protocol":"vitest run tests/e2e/protocol.test.ts","publish-registry:dry-run":"mcp-publisher publish --dry-run"},"_npmUser":{"name":"tan-yong-sheng","email":"tys203831@gmail.com"},"repository":{"url":"git+https://github.com/tan-yong-sheng/ai-vision-mcp.git","type":"git"},"_npmVersion":"10.8.2","description":"Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI","directories":{},"_nodeVersion":"20.20.0","dependencies":{"zod":"^3.23.8","dotenv":"^16.4.5","mime-types":"^2.1.35","node-fetch":"^3.3.2","imagescript":"^1.3.0","@google/genai":"^1.24.0","@google-cloud/storage":"^7.19.0","@modelcontextprotocol/sdk":"^1.26.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"readmeFilename":"README.md","devDependencies":{"knip":"^5.83.1","eslint":"^8.57.0","vitest":"^4.0.18","depcheck":"^1.4.7","prettier":"^3.3.2","ts-prune":"^0.10.3","@types/ws":"^8.18.1","typescript":"^5.5.0","@types/node":"^20.14.0","@types/yauzl":"^2.10.3","@types/phoenix":"^1.6.6","@types/mime-types":"^2.1.4","@types/html-to-text":"^9.0.4","@vitest/coverage-v8":"^4.0.18","eslint-config-prettier":"^9.1.2","eslint-plugin-prettier":"^5.5.4","@typescript-eslint/parser":"^7.18.0","@types/http-cache-semantics":"^4.0.4","@typescript-eslint/eslint-plugin":"^7.18.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-vision-mcp_0.0.5-dev.2_1770870754135_0.5317955955522151","host":"s3://npm-registry-packages-npm-production"}},"0.0.6-dev.1":{"name":"ai-vision-mcp","version":"0.0.6-dev.1","keywords":["mcp","vision","ai","image-analysis","video-analysis","gemini","vertex-ai","google-ai"],"author":{"name":"Tan Yong Sheng","email":"tys203831@gmail.com"},"license":"MIT","_id":"ai-vision-mcp@0.0.6-dev.1","maintainers":[{"name":"tan-yong-sheng","email":"tys203831@gmail.com"}],"homepage":"https://github.com/tan-yong-sheng/ai-vision-mcp#readme","bugs":{"url":"https://github.com/tan-yong-sheng/ai-vision-mcp/issues"},"bin":{"ai-vision":"dist/index.js","ai-vision-mcp":"dist/index.js"},"dist":{"shasum":"54460f8e797f1516533c027a8efd78ecc06d734f","tarball":"https://registry.npmjs.org/ai-vision-mcp/-/ai-vision-mcp-0.0.6-dev.1.tgz","fileCount":183,"integrity":"sha512-JMA1E8AWGWUrHPwNWJdJazGCcUoKSh8dXB8SikaZYxwz82yxoWmj58Wv+44546qdh+wRsGGPMBC8CY1DTkbWag==","signatures":[{"sig":"MEUCIHPuHYvvKkmHY28Ofqc3Bkxxikb0lJ3h1eQN7VS+GnhiAiEAkVoIcJtBlvLL044gLVQq6ElneZ1jaBGJ7h18w+TC6iA=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/ai-vision-mcp@0.0.6-dev.1","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":540480},"main":"dist/index.js","type":"module","types":"./dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"7728d0e277c064a3fca7370455cf5c3fa0765644","scripts":{"dev":"tsc --watch","lint":"eslint src/**/*.ts","test":"vitest run","build":"tsc","start":"node dist/index.js","doctor":"npm run check:imagescript","format":"prettier --write src/**/*.ts","prepare":"npm run build","version":"npm run format && git add -A src","lint:fix":"eslint src/**/*.ts --fix","test:e2e":"vitest run tests/e2e","preversion":"npm run lint","test:watch":"vitest watch","postversion":"git push && git push --tags","test:e2e:ci":"vitest run tests/e2e/protocol.test.ts tests/e2e/validation.test.ts","test:e2e:cli":"vitest run tests/e2e/cli.test.ts","prepublishOnly":"npm run lint","publish-registry":"mcp-publisher publish","check:imagescript":"node -e \"import('imagescript').then(()=>console.error('imagescript:ok')).catch(e=>{console.error('imagescript:fail'); console.error(e&&e.message||e); process.exit(1);})\"","test:e2e:protocol":"vitest run tests/e2e/protocol.test.ts","publish-registry:dry-run":"mcp-publisher publish --dry-run"},"_npmUser":{"name":"tan-yong-sheng","email":"tys203831@gmail.com"},"repository":{"url":"git+https://github.com/tan-yong-sheng/ai-vision-mcp.git","type":"git"},"_npmVersion":"10.8.2","description":"Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI","directories":{},"_nodeVersion":"20.20.0","dependencies":{"zod":"^3.23.8","dotenv":"^16.4.5","mime-types":"^2.1.35","node-fetch":"^3.3.2","imagescript":"^1.3.0","@google/genai":"^1.24.0","@google-cloud/storage":"^7.19.0","@modelcontextprotocol/sdk":"^1.26.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"readmeFilename":"README.md","devDependencies":{"knip":"^5.83.1","eslint":"^8.57.0","vitest":"^4.0.18","depcheck":"^1.4.7","prettier":"^3.3.2","ts-prune":"^0.10.3","@types/ws":"^8.18.1","typescript":"^5.5.0","@types/node":"^20.14.0","@types/yauzl":"^2.10.3","@types/phoenix":"^1.6.6","@types/mime-types":"^2.1.4","@types/html-to-text":"^9.0.4","@vitest/coverage-v8":"^4.0.18","eslint-config-prettier":"^9.1.2","eslint-plugin-prettier":"^5.5.4","@typescript-eslint/parser":"^7.18.0","@types/http-cache-semantics":"^4.0.4","@typescript-eslint/eslint-plugin":"^7.18.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-vision-mcp_0.0.6-dev.1_1770889940468_0.39575770576232205","host":"s3://npm-registry-packages-npm-production"}},"0.0.6-dev.2":{"name":"ai-vision-mcp","version":"0.0.6-dev.2","keywords":["mcp","vision","ai","image-analysis","video-analysis","gemini","vertex-ai","google-ai"],"author":{"name":"Tan Yong Sheng","email":"tys203831@gmail.com"},"license":"MIT","_id":"ai-vision-mcp@0.0.6-dev.2","maintainers":[{"name":"tan-yong-sheng","email":"tys203831@gmail.com"}],"homepage":"https://github.com/tan-yong-sheng/ai-vision-mcp#readme","bugs":{"url":"https://github.com/tan-yong-sheng/ai-vision-mcp/issues"},"bin":{"ai-vision":"dist/index.js","ai-vision-mcp":"dist/index.js"},"dist":{"shasum":"55dd4d4e90e8af90de912e02f488f4747f77d484","tarball":"https://registry.npmjs.org/ai-vision-mcp/-/ai-vision-mcp-0.0.6-dev.2.tgz","fileCount":183,"integrity":"sha512-RxB1LBMXkHlgYdDF5KWa2S8qEmOrLDgigcnZodsQnoBxtJzaUfyzW8tPxNhO8y50yhCxPc/vVh7vbLXNxaiuew==","signatures":[{"sig":"MEYCIQCldFH3vmuv3O6k9TvjyqU3MsT0Hs6lLjKKCKsGTKzxaAIhAOAM1RilonS4KGEfmtvVvbCvNJf91uVSTe20DOlpxmro","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/ai-vision-mcp@0.0.6-dev.2","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":540480},"main":"dist/index.js","type":"module","types":"./dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"b120ae4be606f529f608e21a25dfc0dce5fa968f","scripts":{"dev":"tsc --watch","lint":"eslint src/**/*.ts","test":"vitest run","build":"tsc","start":"node dist/index.js","doctor":"npm run check:imagescript","format":"prettier --write src/**/*.ts","prepare":"npm run build","version":"npm run format && git add -A src","lint:fix":"eslint src/**/*.ts --fix","test:e2e":"vitest run tests/e2e","preversion":"npm run lint","test:watch":"vitest watch","postversion":"git push && git push --tags","test:e2e:ci":"vitest run tests/e2e/protocol.test.ts tests/e2e/validation.test.ts","test:e2e:cli":"vitest run tests/e2e/cli.test.ts","prepublishOnly":"npm run lint","publish-registry":"mcp-publisher publish","check:imagescript":"node -e \"import('imagescript').then(()=>console.error('imagescript:ok')).catch(e=>{console.error('imagescript:fail'); console.error(e&&e.message||e); process.exit(1);})\"","test:e2e:protocol":"vitest run tests/e2e/protocol.test.ts","publish-registry:dry-run":"mcp-publisher publish --dry-run"},"_npmUser":{"name":"tan-yong-sheng","email":"tys203831@gmail.com"},"repository":{"url":"git+https://github.com/tan-yong-sheng/ai-vision-mcp.git","type":"git"},"_npmVersion":"10.8.2","description":"Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI","directories":{},"_nodeVersion":"20.20.0","dependencies":{"zod":"^3.23.8","dotenv":"^16.4.5","mime-types":"^2.1.35","node-fetch":"^3.3.2","imagescript":"^1.3.0","@google/genai":"^1.24.0","@google-cloud/storage":"^7.19.0","@modelcontextprotocol/sdk":"^1.26.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"readmeFilename":"README.md","devDependencies":{"knip":"^5.83.1","eslint":"^8.57.0","vitest":"^4.0.18","depcheck":"^1.4.7","prettier":"^3.3.2","ts-prune":"^0.10.3","@types/ws":"^8.18.1","typescript":"^5.5.0","@types/node":"^20.14.0","@types/yauzl":"^2.10.3","@types/phoenix":"^1.6.6","@types/mime-types":"^2.1.4","@types/html-to-text":"^9.0.4","@vitest/coverage-v8":"^4.0.18","eslint-config-prettier":"^9.1.2","eslint-plugin-prettier":"^5.5.4","@typescript-eslint/parser":"^7.18.0","@types/http-cache-semantics":"^4.0.4","@typescript-eslint/eslint-plugin":"^7.18.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-vision-mcp_0.0.6-dev.2_1770895542518_0.45789995804847927","host":"s3://npm-registry-packages-npm-production"}},"0.0.6":{"name":"ai-vision-mcp","version":"0.0.6","keywords":["mcp","vision","ai","image-analysis","video-analysis","gemini","vertex-ai","google-ai"],"author":{"name":"Tan Yong Sheng","email":"tys203831@gmail.com"},"license":"MIT","_id":"ai-vision-mcp@0.0.6","maintainers":[{"name":"tan-yong-sheng","email":"tys203831@gmail.com"}],"homepage":"https://github.com/tan-yong-sheng/ai-vision-mcp#readme","bugs":{"url":"https://github.com/tan-yong-sheng/ai-vision-mcp/issues"},"bin":{"ai-vision":"dist/index.js","ai-vision-mcp":"dist/index.js"},"dist":{"shasum":"7cd19012cf02a55b388a5a67e933907c8b0a83e7","tarball":"https://registry.npmjs.org/ai-vision-mcp/-/ai-vision-mcp-0.0.6.tgz","fileCount":179,"integrity":"sha512-wwabY3NrGpqiy385E8zETWJYJ+drhzorqr5h1bqRzW4kv4DQBCpLbTe1sx7rs6F/NO0cacU/cf1w27XRY9yz2A==","signatures":[{"sig":"MEQCIHF+mPzUwfSdz90fOz/tJ5/8n0ciSAk7sDMV0Je5k1UFAiBPHnSX4G9V5PS+XCJIdmcbv3gyB47DrtShwvrO9ee3bQ==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/ai-vision-mcp@0.0.6","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":532174},"main":"dist/index.js","type":"module","types":"./dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"8b510eb94f83c086dd567535687864434daf5bb5","scripts":{"dev":"tsc --watch","lint":"eslint src/**/*.ts","test":"vitest run","build":"tsc","start":"node dist/index.js","doctor":"npm run check:imagescript","format":"prettier --write src/**/*.ts","prepare":"npm run build","version":"npm run format && git add -A src","lint:fix":"eslint src/**/*.ts --fix","test:e2e":"vitest run tests/e2e","preversion":"npm run lint","test:watch":"vitest watch","postversion":"git push && git push --tags","test:e2e:ci":"vitest run tests/e2e/protocol.test.ts tests/e2e/validation.test.ts","test:e2e:cli":"vitest run tests/e2e/cli.test.ts","prepublishOnly":"npm run lint","publish-registry":"mcp-publisher publish","check:imagescript":"node -e \"import('imagescript').then(()=>console.error('imagescript:ok')).catch(e=>{console.error('imagescript:fail'); console.error(e&&e.message||e); process.exit(1);})\"","test:e2e:protocol":"vitest run tests/e2e/protocol.test.ts","publish-registry:dry-run":"mcp-publisher publish --dry-run"},"_npmUser":{"name":"tan-yong-sheng","email":"tys203831@gmail.com"},"repository":{"url":"git+https://github.com/tan-yong-sheng/ai-vision-mcp.git","type":"git"},"_npmVersion":"10.8.2","description":"Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI","directories":{},"_nodeVersion":"20.20.0","dependencies":{"zod":"^3.23.8","dotenv":"^16.4.5","mime-types":"^2.1.35","node-fetch":"^3.3.2","imagescript":"^1.3.0","@google/genai":"^1.24.0","@google-cloud/storage":"^7.19.0","@modelcontextprotocol/sdk":"^1.26.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"knip":"^5.83.1","eslint":"^8.57.0","vitest":"^4.0.18","depcheck":"^1.4.7","prettier":"^3.3.2","ts-prune":"^0.10.3","@types/ws":"^8.18.1","typescript":"^5.5.0","@types/node":"^20.14.0","@types/yauzl":"^2.10.3","@types/phoenix":"^1.6.6","@types/mime-types":"^2.1.4","@types/html-to-text":"^9.0.4","@vitest/coverage-v8":"^4.0.18","eslint-config-prettier":"^9.1.2","eslint-plugin-prettier":"^5.5.4","@typescript-eslint/parser":"^7.18.0","@types/http-cache-semantics":"^4.0.4","@typescript-eslint/eslint-plugin":"^7.18.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-vision-mcp_0.0.6_1770918289904_0.06468723815125421","host":"s3://npm-registry-packages-npm-production"}},"0.0.7-dev.1":{"name":"ai-vision-mcp","version":"0.0.7-dev.1","keywords":["mcp","vision","ai","image-analysis","video-analysis","gemini","vertex-ai","google-ai"],"author":{"name":"Tan Yong Sheng","email":"tys203831@gmail.com"},"license":"MIT","_id":"ai-vision-mcp@0.0.7-dev.1","maintainers":[{"name":"tan-yong-sheng","email":"tys203831@gmail.com"}],"homepage":"https://github.com/tan-yong-sheng/ai-vision-mcp#readme","bugs":{"url":"https://github.com/tan-yong-sheng/ai-vision-mcp/issues"},"bin":{"ai-vision":"dist/index.js","ai-vision-mcp":"dist/index.js"},"dist":{"shasum":"666075f69d9b515c54ac468555b0c37748225366","tarball":"https://registry.npmjs.org/ai-vision-mcp/-/ai-vision-mcp-0.0.7-dev.1.tgz","fileCount":179,"integrity":"sha512-ABREsDtK7huE+BR+DqzTW8DYN3wYCgmZqEePzeCT/POoSXFG+5aBvw9B20Eau/OnBsLCc7tNWQnjYxbKkwBnvg==","signatures":[{"sig":"MEUCIQDd54s0iDXZigcMMHHkoWtTx9Q9IcvOr7fQ+lSio3SEaQIgMvDlbhEWfABR6+Dqhg3TOZeqqQ247w0lesjX4eCwLLc=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/ai-vision-mcp@0.0.7-dev.1","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":544333},"main":"dist/index.js","type":"module","types":"./dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"3aac7fe4ee85abdcf819125f8ff0cfc6e9eed64c","scripts":{"dev":"tsc --watch","lint":"eslint src/**/*.ts","test":"vitest run","build":"tsc","start":"node dist/index.js","doctor":"npm run check:imagescript","format":"prettier --write src/**/*.ts","prepare":"npm run build","version":"npm run format && git add -A src","lint:fix":"eslint src/**/*.ts --fix","test:e2e":"vitest run tests/e2e","preversion":"npm run lint","test:watch":"vitest watch","postversion":"git push && git push --tags","test:e2e:ci":"vitest run tests/e2e/protocol.test.ts tests/e2e/validation.test.ts","test:e2e:cli":"vitest run tests/e2e/cli.test.ts","prepublishOnly":"npm run lint","publish-registry":"mcp-publisher publish","check:imagescript":"node -e \"import('imagescript').then(()=>console.error('imagescript:ok')).catch(e=>{console.error('imagescript:fail'); console.error(e&&e.message||e); process.exit(1);})\"","test:e2e:protocol":"vitest run tests/e2e/protocol.test.ts","publish-registry:dry-run":"mcp-publisher publish --dry-run"},"_npmUser":{"name":"tan-yong-sheng","email":"tys203831@gmail.com"},"repository":{"url":"git+https://github.com/tan-yong-sheng/ai-vision-mcp.git","type":"git"},"_npmVersion":"10.8.2","description":"Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI","directories":{},"_nodeVersion":"20.20.2","dependencies":{"zod":"^3.23.8","dotenv":"^16.4.5","mime-types":"^2.1.35","node-fetch":"^3.3.2","imagescript":"^1.3.0","@google/genai":"^1.24.0","@google-cloud/storage":"^7.19.0","@modelcontextprotocol/sdk":"^1.26.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"readmeFilename":"README.md","devDependencies":{"knip":"^5.83.1","eslint":"^8.57.0","vitest":"^4.0.18","depcheck":"^1.4.7","prettier":"^3.3.2","ts-prune":"^0.10.3","@types/ws":"^8.18.1","typescript":"^5.5.0","@types/node":"^20.14.0","@types/yauzl":"^2.10.3","@types/phoenix":"^1.6.6","@types/mime-types":"^2.1.4","@types/html-to-text":"^9.0.4","@vitest/coverage-v8":"^4.0.18","eslint-config-prettier":"^9.1.2","eslint-plugin-prettier":"^5.5.4","@typescript-eslint/parser":"^7.18.0","@types/http-cache-semantics":"^4.0.4","@typescript-eslint/eslint-plugin":"^7.18.0"},"_npmOperationalInternal":{"tmp":"tmp/ai-vision-mcp_0.0.7-dev.1_1775209563683_0.41796966413259606","host":"s3://npm-registry-packages-npm-production"}},"0.0.7":{"name":"ai-vision-mcp","version":"0.0.7","description":"Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI","main":"dist/index.js","type":"module","scripts":{"build":"tsc","dev":"tsc --watch","start":"node dist/index.js","lint":"eslint src/**/*.ts","lint:fix":"eslint src/**/*.ts --fix","format":"prettier --write src/**/*.ts","prepare":"npm run build","check:imagescript":"node -e \"import('imagescript').then(()=>console.error('imagescript:ok')).catch(e=>{console.error('imagescript:fail'); console.error(e&&e.message||e); process.exit(1);})\"","doctor":"npm run check:imagescript","prepublishOnly":"npm run lint","preversion":"npm run lint","version":"npm run format && git add -A src","postversion":"git push && git push --tags","publish-registry":"mcp-publisher publish","publish-registry:dry-run":"mcp-publisher publish --dry-run","test":"vitest run","test:e2e":"vitest run tests/e2e","test:e2e:protocol":"vitest run tests/e2e/protocol.test.ts","test:e2e:ci":"vitest run tests/e2e/protocol.test.ts tests/e2e/validation.test.ts","test:e2e:cli":"vitest run tests/e2e/cli.test.ts","test:watch":"vitest watch"},"keywords":["mcp","vision","ai","image-analysis","video-analysis","gemini","vertex-ai","google-ai"],"author":{"name":"Tan Yong Sheng","email":"tys203831@gmail.com"},"license":"MIT","bin":{"ai-vision-mcp":"dist/index.js","ai-vision":"dist/index.js"},"repository":{"type":"git","url":"git+https://github.com/tan-yong-sheng/ai-vision-mcp.git"},"bugs":{"url":"https://github.com/tan-yong-sheng/ai-vision-mcp/issues"},"homepage":"https://github.com/tan-yong-sheng/ai-vision-mcp#readme","dependencies":{"@google-cloud/storage":"^7.19.0","@google/genai":"^1.24.0","@modelcontextprotocol/sdk":"^1.26.0","dotenv":"^16.4.5","imagescript":"^1.3.0","mime-types":"^2.1.35","node-fetch":"^3.3.2","zod":"^3.23.8"},"devDependencies":{"@types/html-to-text":"^9.0.4","@types/http-cache-semantics":"^4.0.4","@types/mime-types":"^2.1.4","@types/node":"^20.14.0","@types/phoenix":"^1.6.6","@types/ws":"^8.18.1","@types/yauzl":"^2.10.3","@typescript-eslint/eslint-plugin":"^7.18.0","@typescript-eslint/parser":"^7.18.0","@vitest/coverage-v8":"^4.0.18","depcheck":"^1.4.7","eslint":"^8.57.0","eslint-config-prettier":"^9.1.2","eslint-plugin-prettier":"^5.5.4","knip":"^5.83.1","prettier":"^3.3.2","ts-prune":"^0.10.3","typescript":"^5.5.0","vitest":"^4.0.18"},"engines":{"node":">=18.0.0"},"publishConfig":{"access":"public"},"_id":"ai-vision-mcp@0.0.7","gitHead":"204d0bf69201bf72ee655e5265aa2893ddaebf35","types":"./dist/index.d.ts","_nodeVersion":"20.20.2","_npmVersion":"10.8.2","dist":{"integrity":"sha512-DJ/v3YgUtjN+1chZSKXIYhf4sl1Zosw6hNTaW7wclSNsFXEeCNXuVJbuE6iWBTa91gRXlawtHTjPzThS2i98RA==","shasum":"6c673136669cbff72611c11c7fd5423d9c807af6","tarball":"https://registry.npmjs.org/ai-vision-mcp/-/ai-vision-mcp-0.0.7.tgz","fileCount":195,"unpackedSize":573784,"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/ai-vision-mcp@0.0.7","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"signatures":[{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEUCIQCjRK1qA4XUGh8bAgsaII577voi163rX4eH3TUiK1bw0AIgGfy6HZUUQ6UNy1fsnWWqvUWLQUj7KZVwIWSfg0lZH7g="}]},"_npmUser":{"name":"tan-yong-sheng","email":"tys203831@gmail.com"},"directories":{},"maintainers":[{"name":"tan-yong-sheng","email":"tys203831@gmail.com"}],"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/ai-vision-mcp_0.0.7_1775298037055_0.9723089489707646"},"_hasShrinkwrap":false}},"time":{"created":"2025-10-05T14:17:02.520Z","modified":"2026-04-04T10:20:37.601Z","0.0.1":"2025-10-05T14:17:02.777Z","0.0.2":"2025-10-06T03:15:05.684Z","0.0.3":"2025-10-10T10:06:21.818Z","0.0.4":"2025-10-11T04:27:42.952Z","0.0.4-beta":"2025-10-11T04:43:14.857Z","0.0.5":"2025-10-11T04:56:30.905Z","0.0.5-dev.20260211.411de3c":"2026-02-11T06:43:05.861Z","0.0.5-dev.20260211.3638630":"2026-02-11T07:05:21.457Z","0.0.5-dev.20260211.335468b":"2026-02-11T07:07:30.369Z","0.0.5-dev.20260211.6cf3ff2":"2026-02-11T07:19:13.459Z","0.0.5-dev.20260211.a510d24":"2026-02-11T12:49:58.016Z","0.0.5-dev.20260211.5498e54":"2026-02-11T12:54:10.282Z","0.0.5-dev.20260211.d766dc0":"2026-02-11T13:25:40.585Z","0.0.5-dev.20260211.7addf1a":"2026-02-11T13:32:28.273Z","0.0.5-dev.1":"2026-02-11T17:48:13.482Z","0.0.5-dev.2":"2026-02-12T04:32:34.289Z","0.0.6-dev.1":"2026-02-12T09:52:20.624Z","0.0.6-dev.2":"2026-02-12T11:25:42.669Z","0.0.6":"2026-02-12T17:44:50.084Z","0.0.7-dev.1":"2026-04-03T09:46:03.839Z","0.0.7":"2026-04-04T10:20:37.240Z"},"bugs":{"url":"https://github.com/tan-yong-sheng/ai-vision-mcp/issues"},"author":{"name":"Tan Yong Sheng","email":"tys203831@gmail.com"},"license":"MIT","homepage":"https://github.com/tan-yong-sheng/ai-vision-mcp#readme","keywords":["mcp","vision","ai","image-analysis","video-analysis","gemini","vertex-ai","google-ai"],"repository":{"type":"git","url":"git+https://github.com/tan-yong-sheng/ai-vision-mcp.git"},"description":"Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI","maintainers":[{"name":"tan-yong-sheng","email":"tys203831@gmail.com"}],"readme":"# AI Vision MCP Server\n\nA powerful Model Context Protocol (MCP) server that provides AI-powered image and video analysis using Google Gemini and Vertex AI models.\n\n## Features\n\n- **Dual Provider Support**: Choose between Google Gemini API and Vertex AI\n- **Multimodal Analysis**: Support for both image and video content analysis\n- **Flexible File Handling**: Upload via multiple methods (URLs, local files, base64)\n- **Storage Integration**: Built-in Google Cloud Storage support\n- **Comprehensive Validation**: Zod-based data validation throughout\n- **Error Handling**: Robust error handling with retry logic and circuit breakers\n- **TypeScript**: Full TypeScript support with strict type checking\n\n\n## Quick Start\n\n### Pre-requisites\n\nYou could choose either to use [`google` provider](https://aistudio.google.com/welcome) or [`vertex_ai` provider](https://cloud.google.com/vertex-ai/generative-ai/docs/start/quickstart). For simplicity, `google` provider is recommended.\n\nBelow are the environment variables you need to set based on your selected provider. (Note: It’s recommended to set the timeout configuration to more than 5 minutes for your MCP client).\n\n(i) **Using Google AI Studio Provider**\n\n```bash\nexport IMAGE_PROVIDER=\"google\" # or vertex_ai\nexport VIDEO_PROVIDER=\"google\" # or vertex_ai\nexport GEMINI_API_KEY=\"your-gemini-api-key\"\n```\n\nGet your Google AI Studio's api key [here](https://aistudio.google.com/app/api-keys)\n\n(ii) **Using Vertex AI Provider**\n\n```bash\nexport IMAGE_PROVIDER=\"vertex_ai\"\nexport VIDEO_PROVIDER=\"vertex_ai\"\nexport VERTEX_CLIENT_EMAIL=\"your-service-account@project.iam.gserviceaccount.com\"\nexport VERTEX_PRIVATE_KEY=\"-----BEGIN PRIVATE KEY-----\\n...\\n-----END PRIVATE KEY-----\\n\"\nexport VERTEX_PROJECT_ID=\"your-gcp-project-id\"\nexport GCS_BUCKET_NAME=\"your-gcs-bucket\"\n```\n\nRefer to [the guideline here](docs/provider/vertex-ai-setup-guide.md) on how to set this up.\n\n\n### Installation\n\nBelow are the installation guide for this MCP on different MCP clients, such as Claude Desktop, Claude Code, Cursor, Cline, etc.\n\n<details>\n<summary>Claude Desktop</summary>\n\nAdd to your Claude Desktop configuration:\n\n(i) Using Google AI Studio Provider\n```json\n{\n  \"mcpServers\": {\n    \"ai-vision-mcp\": {\n      \"command\": \"npx\",\n      \"args\": [\"ai-vision-mcp\"],\n      \"env\": {\n        \"IMAGE_PROVIDER\": \"google\",\n        \"VIDEO_PROVIDER\": \"google\",\n        \"GEMINI_API_KEY\": \"your-gemini-api-key\"\n      }\n    }\n  }\n}\n```\n\n(ii) Using Vertex AI Provider\n```json\n{\n  \"mcpServers\": {\n    \"ai-vision-mcp\": {\n      \"command\": \"npx\",\n      \"args\": [\"ai-vision-mcp\"],\n      \"env\": {\n        \"IMAGE_PROVIDER\": \"vertex_ai\",\n        \"VIDEO_PROVIDER\": \"vertex_ai\",\n        \"VERTEX_CLIENT_EMAIL\": \"your-service-account@project.iam.gserviceaccount.com\",\n        \"VERTEX_PRIVATE_KEY\": \"-----BEGIN PRIVATE KEY-----\\n...\\n-----END PRIVATE KEY-----\\n\",\n        \"VERTEX_PROJECT_ID\": \"your-gcp-project-id\",\n        \"GCS_BUCKET_NAME\": \"ai-vision-mcp-{VERTEX_PROJECT_ID}\"\n      }\n    }\n  }\n}\n```\n\n</details>\n\n<details>\n<summary>Claude Code</summary>\n\n(i) Using Google AI Studio Provider\n```bash\nclaude mcp add ai-vision-mcp \\\n  -e IMAGE_PROVIDER=google \\\n  -e VIDEO_PROVIDER=google \\\n  -e GEMINI_API_KEY=your-gemini-api-key \\\n  -- npx ai-vision-mcp\n```\n\n(ii) Using Vertex AI Provider\n```bash\nclaude mcp add ai-vision-mcp \\\n  -e IMAGE_PROVIDER=vertex_ai \\\n  -e VIDEO_PROVIDER=vertex_ai \\\n  -e VERTEX_CLIENT_EMAIL=your-service-account@project.iam.gserviceaccount.com \\\n  -e VERTEX_PRIVATE_KEY=\"-----BEGIN PRIVATE KEY-----\\n...\\n-----END PRIVATE KEY-----\\n\" \\\n  -e VERTEX_PROJECT_ID=your-gcp-project-id \\\n  -e GCS_BUCKET_NAME=ai-vision-mcp-{VERTEX_PROJECT_ID} \\\n  -- npx ai-vision-mcp\n```\n\n\nNote: Increase the MCP startup timeout to 1 minutes and MCP tool execution timeout to about 5 minutes by updating `~\\.claude\\settings.json` as follows:\n\n```json\n{\n  \"env\": {\n    \"MCP_TIMEOUT\": \"60000\",\n    \"MCP_TOOL_TIMEOUT\": \"300000\"\n  }\n}\n```\n\n</details>\n\n<details>\n<summary>Cursor</summary>\n\nGo to: Settings -> Cursor Settings -> MCP -> Add new global MCP server\n\nPasting the following configuration into your Cursor ~/.cursor/mcp.json file is the recommended approach. You may also install in a specific project by creating .cursor/mcp.json in your project folder. See [Cursor MCP docs](https://docs.cursor.com/context/model-context-protocol) for more info.\n\n(i) Using Google AI Studio Provider\n```json\n{\n  \"mcpServers\": {\n    \"ai-vision-mcp\": {\n      \"command\": \"npx\",\n      \"args\": [\"ai-vision-mcp\"],\n      \"env\": {\n        \"IMAGE_PROVIDER\": \"google\",\n        \"VIDEO_PROVIDER\": \"google\",\n        \"GEMINI_API_KEY\": \"your-gemini-api-key\"\n      }\n    }\n  }\n}\n```\n\n(ii) Using Vertex AI Provider\n```json\n{\n  \"mcpServers\": {\n    \"ai-vision-mcp\": {\n      \"command\": \"npx\",\n      \"args\": [\"ai-vision-mcp\"],\n      \"env\": {\n        \"IMAGE_PROVIDER\": \"vertex_ai\",\n        \"VIDEO_PROVIDER\": \"vertex_ai\",\n        \"VERTEX_CLIENT_EMAIL\": \"your-service-account@project.iam.gserviceaccount.com\",\n        \"VERTEX_PRIVATE_KEY\": \"-----BEGIN PRIVATE KEY-----\\n...\\n-----END PRIVATE KEY-----\\n\",\n        \"VERTEX_PROJECT_ID\": \"your-gcp-project-id\",\n        \"GCS_BUCKET_NAME\": \"ai-vision-mcp-{VERTEX_PROJECT_ID}\"\n      }\n    }\n  }\n}\n```\n</details>\n\n\n<details>\n<summary>Cline</summary>\n\nCline uses a JSON configuration file to manage MCP servers. To integrate the provided MCP server configuration:\n\n1. Open Cline and click on the MCP Servers icon in the top navigation bar.\n2. Select the Installed tab, then click Advanced MCP Settings.\n3. In the cline_mcp_settings.json file, add the following configuration:\n\n(i) Using Google AI Studio Provider\n```json\n{\n  \"mcpServers\": {\n    \"timeout\": 300, \n    \"type\": \"stdio\",\n    \"ai-vision-mcp\": {\n      \"command\": \"npx\",\n      \"args\": [\"ai-vision-mcp\"],\n      \"env\": {\n        \"IMAGE_PROVIDER\": \"google\",\n        \"VIDEO_PROVIDER\": \"google\",\n        \"GEMINI_API_KEY\": \"your-gemini-api-key\"\n      }\n    }\n  }\n}\n```\n\n(ii) Using Vertex AI Provider\n```json\n{\n  \"mcpServers\": {\n    \"ai-vision-mcp\": {\n      \"timeout\": 300,\n      \"type\": \"stdio\",\n      \"command\": \"npx\",\n      \"args\": [\"ai-vision-mcp\"],\n      \"env\": {\n        \"IMAGE_PROVIDER\": \"vertex_ai\",\n        \"VIDEO_PROVIDER\": \"vertex_ai\",\n        \"VERTEX_CLIENT_EMAIL\": \"your-service-account@project.iam.gserviceaccount.com\",\n        \"VERTEX_PRIVATE_KEY\": \"-----BEGIN PRIVATE KEY-----\\n...\\n-----END PRIVATE KEY-----\\n\",\n        \"VERTEX_PROJECT_ID\": \"your-gcp-project-id\",\n        \"GCS_BUCKET_NAME\": \"ai-vision-mcp-{VERTEX_PROJECT_ID}\"\n      }\n    }\n  }\n}\n```\n</details>\n\n\n<details>\n\n<summary>Other MCP clients</summary>\n\nThe server uses stdio transport and follows the standard MCP protocol. It can be integrated with any MCP-compatible client by running:\n\n```bash\nnpx ai-vision-mcp\n```\n</details>\n\n\n## MCP Tools\n\nThe server provides four main MCP tools:\n\n### 1) `analyze_image`\n\nAnalyzes an image using AI and returns a detailed description.\n\n**Parameters:**\n- `imageSource` (string): URL, base64 data, or file path to the image\n- `prompt` (string): Question or instruction for the AI\n- `options` (object, optional): Analysis options including temperature and max tokens\n\n**Examples:**\n\n1. **Analyze image from URL:**\n```json\n{\n  \"imageSource\": \"https://plus.unsplash.com/premium_photo-1710965560034-778eedc929ff\",\n  \"prompt\": \"What is this image about? Describe what you see in detail.\"\n}\n```\n\n2. **Analyze local image file:**\n```json\n{\n  \"imageSource\": \"C:\\\\Users\\\\username\\\\Downloads\\\\image.jpg\",\n  \"prompt\": \"What is this image about? Describe what you see in detail.\"\n}\n```\n\n\n### 2) `compare_images`\n\nCompares multiple images using AI and returns a detailed comparison analysis.\n\n**Parameters:**\n- `imageSources` (array): Array of image sources (URLs, base64 data, or file paths) - minimum 2, maximum 4 images\n- `prompt` (string): Question or instruction for comparing the images\n- `options` (object, optional): Analysis options including temperature and max tokens\n\n**Examples:**\n\n1. **Compare images from URLs:**\n```json\n{\n  \"imageSources\": [\n    \"https://example.com/image1.jpg\",\n    \"https://example.com/image2.jpg\"\n  ],\n  \"prompt\": \"Compare these two images and tell me the differences\"\n}\n```\n\n2. **Compare mixed sources:**\n```json\n{\n  \"imageSources\": [\n    \"https://example.com/image1.jpg\",\n    \"C:\\\\\\\\Users\\\\\\\\username\\\\\\\\Downloads\\\\\\\\image2.jpg\",\n    \"data:image/jpeg;base64,/9j/4AAQSkZJRgAB...\"\n  ],\n  \"prompt\": \"Which image has the best lighting quality?\"\n}\n```\n\n### 3) `detect_objects_in_image`\n\nDetects objects in an image using AI vision models and generates annotated images with bounding boxes. Returns detected objects with coordinates and either saves the annotated image to a file or temporary directory.\n\n**Parameters:**\n- `imageSource` (string): URL, base64 data, or file path to the image\n- `prompt` (string): Custom detection prompt describing what to detect or recognize in the image\n- `outputFilePath` (string, optional): Explicit output path for the annotated image\n\n**Configuration:**\nThis function uses optimized default parameters for object detection and does not accept runtime `options` parameter. To customize the AI parameters (temperature, topP, topK, maxTokens), use environment variables:\n\n```\n# Recommended environment variable settings for object detection (these are now the defaults)\nTEMPERATURE_FOR_DETECT_OBJECTS_IN_IMAGE=0.0     # Deterministic responses\nTOP_P_FOR_DETECT_OBJECTS_IN_IMAGE=0.95          # Nucleus sampling\nTOP_K_FOR_DETECT_OBJECTS_IN_IMAGE=30            # Vocabulary selection\nMAX_TOKENS_FOR_DETECT_OBJECTS_IN_IMAGE=8192     # High token limit for JSON\n```\n\n**File Handling Logic:**\n1. **Explicit outputFilePath provided** → Saves to the exact path specified\n2. **If not explicit outputFilePath** → Automatically saves to temporary directory\n\n**Response Types:**\n- Returns `file` object when explicit outputFilePath is provided\n- Returns `tempFile` object when explicit outputFilePath is not provided so the image file output is auto-saved to temporary folder\n- Always includes `detections` array with detected objects and coordinates\n- Includes `summary` with percentage-based coordinates for browser automation\n\n**Examples:**\n\n1. **Basic object detection:**\n```json\n{\n  \"imageSource\": \"https://example.com/image.jpg\",\n  \"prompt\": \"Detect all objects in this image\"\n}\n```\n\n2. **Save annotated image to specific path:**\n```json\n{\n  \"imageSource\": \"C:\\\\Users\\\\username\\\\Downloads\\\\image.jpg\",\n  \"outputFilePath\": \"C:\\\\Users\\\\username\\\\Documents\\\\annotated_image.png\"\n}\n```\n\n3. **Custom detection prompt:**\n```json\n{\n  \"imageSource\": \"data:image/jpeg;base64,/9j/4AAQSkZJRgAB...\",\n  \"prompt\": \"Detect and label all electronic devices in this image\"\n}\n```\n\n\n### 4) `analyze_video`\n\nAnalyzes a video using AI and returns a detailed description.\n\n**Parameters:**\n- `videoSource` (string): YouTube URL, GCS URI, or local file path to the video\n- `prompt` (string): Question or instruction for the AI\n- `options` (object, optional): Analysis options including temperature and max tokens\n\n**Supported video sources:**\n- YouTube URLs (e.g., `https://www.youtube.com/watch?v=...`)\n- Local file paths (e.g., `C:\\Users\\username\\Downloads\\video.mp4`)\n\n**Examples:**\n\n1. **Analyze video from YouTube URL:**\n```json\n{\n  \"videoSource\": \"https://www.youtube.com/watch?v=9hE5-98ZeCg\",\n  \"prompt\": \"What is this video about? Describe what you see in detail.\"\n}\n```\n\n2. **Analyze local video file:**\n```json\n{\n  \"videoSource\": \"C:\\\\Users\\\\username\\\\Downloads\\\\video.mp4\",\n  \"prompt\": \"What is this video about? Describe what you see in detail.\"\n}\n```\n\n**Note:** Only YouTube URLs are supported for public video URLs. Other public video URLs are not currently supported.\n\n\n## Environment Configuration\n\nFor basic setup, you only need to configure the provider selection and required credentials:\n\n### Google AI Studio Provider (Recommended)\n```bash\nexport IMAGE_PROVIDER=\"google\"\nexport VIDEO_PROVIDER=\"google\"\nexport GEMINI_API_KEY=\"your-gemini-api-key\"\n```\n\n### Vertex AI Provider (Production)\n```bash\nexport IMAGE_PROVIDER=\"vertex_ai\"\nexport VIDEO_PROVIDER=\"vertex_ai\"\nexport VERTEX_CLIENT_EMAIL=\"your-service-account@project.iam.gserviceaccount.com\"\nexport VERTEX_PRIVATE_KEY=\"-----BEGIN PRIVATE KEY-----\\n...\\n-----END PRIVATE KEY-----\\n\"\nexport VERTEX_PROJECT_ID=\"your-gcp-project-id\"\nexport GCS_BUCKET_NAME=\"your-gcs-bucket\"\n```\n\n### 📖 **Detailed Configuration Guide**\n\nFor comprehensive environment variable documentation, including:\n- Complete configuration reference (60+ environment variables)\n- Function-specific optimization examples\n- Advanced configuration patterns\n- Troubleshooting guidance\n\n👉 **[See Environment Variable Guide](docs/environment-variable-guide.md)**\n\n### Configuration Priority Overview\n\nThe server uses a hierarchical configuration system where more specific settings override general ones:\n\n1. **LLM-assigned values** (runtime parameters in tool calls)\n2. **Function-specific variables** (`TEMPERATURE_FOR_ANALYZE_IMAGE`, etc.)\n3. **Task-specific variables** (`TEMPERATURE_FOR_IMAGE`, etc.)\n4. **Universal variables** (`TEMPERATURE`, etc.)\n5. **System defaults**\n\n<details>\n<summary><strong>Quick Configuration Examples</strong></summary>\n\n**Basic Optimization:**\n```bash\n# General settings\nexport TEMPERATURE=0.7\nexport MAX_TOKENS=1500\n\n# Task-specific optimization\nexport TEMPERATURE_FOR_IMAGE=0.2     # More precise for images\nexport TEMPERATURE_FOR_VIDEO=0.5     # More creative for videos\n```\n\n**Function-specific Optimization:**\n```bash\n# Optimize individual functions\nexport TEMPERATURE_FOR_ANALYZE_IMAGE=0.1\nexport TEMPERATURE_FOR_COMPARE_IMAGES=0.3\nexport TEMPERATURE_FOR_DETECT_OBJECTS_IN_IMAGE=0.0  # Deterministic\nexport MAX_TOKENS_FOR_DETECT_OBJECTS_IN_IMAGE=8192   # High token limit\n```\n\n**Model Selection:**\n```bash\n# Choose models per function\nexport ANALYZE_IMAGE_MODEL=\"gemini-2.5-flash-lite\"\nexport COMPARE_IMAGES_MODEL=\"gemini-2.5-flash\"\nexport ANALYZE_VIDEO_MODEL=\"gemini-2.5-flash-pro\"\n```\n</details>\n\n## Troubleshooting (stdio / Codex / Claude Code)\n\n### 1) \"Transport closed\" / tool call fails\n\nIf you see errors like:\n\n- `tools/call failed: Transport closed`\n\nCommon causes:\n\n**A) Image annotation dependency failed to load**\n\nThis server uses [`imagescript`](https://github.com/matmen/ImageScript) for image annotation/dimension extraction.\n\nVerify it loads:\n\n```bash\nnpm run doctor\n# or\nnpm run check:imagescript\n```\n\n**B) stdout logs corrupt stdio MCP framing**\n\nThis server uses the MCP **stdio** transport (newline-delimited JSON-RPC over stdout).\n\n- ✅ stdout must contain **only** MCP JSON-RPC messages\n- ✅ write logs to **stderr** (e.g. `console.error`)\n- ❌ do not use `console.log` in stdio MCP servers\n\nIf stdout is polluted, clients (Codex/Claude Code) may disconnect and report `Transport closed`.\n\n## Development\n\n### Prerequisites\n\n- Node.js 18+\n- npm or yarn\n\n### Setup\n\n```bash\n# Clone the repository\ngit clone https://github.com/tan-yong-sheng/ai-vision-mcp.git\ncd ai-vision-mcp\n\n# Install dependencies\nnpm install\n\n# Build the project\nnpm run build\n\n# Start development server\nnpm run dev\n```\n\n### Scripts\n\n- `npm run build` - Build the TypeScript project\n- `npm run dev` - Start development server with watch mode\n- `npm run lint` - Run ESLint\n- `npm run format` - Format code with Prettier\n- `npm start` - Start the built server\n\n## Architecture\n\nThe project follows a modular architecture:\n\n```\nsrc/\n├── providers/          # AI provider implementations\n│   ├── gemini/        # Google Gemini provider\n│   ├── vertexai/      # Vertex AI provider\n│   └── factory/       # Provider factory\n├── services/          # Core services\n│   ├── ConfigService.ts\n│   └── FileService.ts\n├── storage/           # Storage implementations\n├── file-upload/       # File upload strategies\n├── types/            # TypeScript type definitions\n├── utils/            # Utility functions\n└── server.ts         # Main MCP server\n```\n\n## Error Handling\n\nThe server includes comprehensive error handling:\n\n- **Validation Errors**: Input validation using Zod schemas\n- **Network Errors**: Automatic retries with exponential backoff\n- **Authentication Errors**: Clear error messages for API key issues\n- **File Errors**: Handling for file size limits and format restrictions\n\n## Contributing\n\n1. Fork the repository\n2. Create a feature branch (`git checkout -b feature/amazing-feature`)\n3. Commit your changes (`git commit -m 'Add amazing feature'`)\n4. Push to the branch (`git push origin feature/amazing-feature`)\n5. Open a Pull Request\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## Acknowledgments\n\n- Google for the Gemini and Vertex AI APIs\n- The Model Context Protocol team for the MCP framework\n- All contributors and users of this project","readmeFilename":"README.md"}