{"_id":"@jim-panse/pdf-to-text-mcp","_rev":"12-7473969698a9358550e30f84932d31fb","name":"@jim-panse/pdf-to-text-mcp","dist-tags":{"latest":"0.7.0"},"versions":{"0.4.3":{"name":"@jim-panse/pdf-to-text-mcp","version":"0.4.3","keywords":["pdf","text-extraction","ocr","mcp","model-context-protocol"],"license":"AGPL-3.0-only","_id":"@jim-panse/pdf-to-text-mcp@0.4.3","maintainers":[{"name":"jim-panse","email":"jim-panse-1@posteo.de"}],"homepage":"https://github.com/Jim-Panse/PDF-to-TXT-MCP#readme","bugs":{"url":"https://github.com/Jim-Panse/PDF-to-TXT-MCP/issues"},"bin":{"pdf-to-text-mcp":"dist/index.js"},"dist":{"shasum":"a3c4f2227157886004c225006f50e401e27d6751","tarball":"https://registry.npmjs.org/@jim-panse/pdf-to-text-mcp/-/pdf-to-text-mcp-0.4.3.tgz","fileCount":5,"integrity":"sha512-yPe3nJ0zjytsUYIIw05NLv9Tnu0gmU9EEBvhBf19CmXzTuFFnHwAYoH9l/Bsljvn/tXvtunPXjsoCDZPLxATyQ==","signatures":[{"sig":"MEQCIG1N2OcxQDpH1QofONUKkkAe+VyS4zlOS0EBRTwiF2B8AiBzMai1YkZ6U1z9oqJrx9Nj9SZUMuPKIvI3tBv2uO9B7Q==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEQCIEHxqFb60ZmEhjOn5yAO86TEK7X6hO8oX/y+52xNWEB9AiAEe8Wt5AoT5vwpLiiZq7co0lvQEY9rQj72cjTg0G4ghQ==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":68551},"type":"module","_from":"file:jim-panse-pdf-to-text-mcp-0.4.3.tgz","engines":{"node":">=22.13.0"},"mcpName":"io.github.Jim-Panse/pdf-to-text","scripts":{"dev":"tsx watch src/index.ts","test":"vitest run","build":"tsc -p tsconfig.json --noEmit && node scripts/build.mjs","start":"node dist/index.js","prepack":"npm run build"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"4ff760c3-5a7c-4c68-ab04-79e53e0d945e"}},"_resolved":"/Users/runner/work/PDF-to-TXT-MCP/PDF-to-TXT-MCP/jim-panse-pdf-to-text-mcp-0.4.3.tgz","_integrity":"sha512-yPe3nJ0zjytsUYIIw05NLv9Tnu0gmU9EEBvhBf19CmXzTuFFnHwAYoH9l/Bsljvn/tXvtunPXjsoCDZPLxATyQ==","repository":{"url":"git+https://github.com/Jim-Panse/PDF-to-TXT-MCP.git","type":"git"},"_npmVersion":"11.21.0","description":"MCP server for extracting text from PDF files.","directories":{},"_nodeVersion":"22.23.2","dependencies":{"zod":"^4.4.3","openai":"^6.45.0","pdfjs-dist":"^6.0.227","@modelcontextprotocol/sdk":"^1.29.0"},"publishConfig":{"access":"public","registry":"https://registry.npmjs.org/"},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.20.6","terser":"^5.51.2","vitest":"^5.0.3","esbuild":"^0.28.1","typescript":"^5.9.3","@types/node":"^25.3.0"},"_npmOperationalInternal":{"tmp":"tmp/pdf-to-text-mcp_0.4.3_1791641074358_0.7563258845179126","host":"s3://npm-registry-packages-npm-production"}},"0.4.4":{"name":"@jim-panse/pdf-to-text-mcp","version":"0.4.4","keywords":["pdf","text-extraction","ocr","mcp","model-context-protocol"],"license":"AGPL-3.0-only","_id":"@jim-panse/pdf-to-text-mcp@0.4.4","maintainers":[{"name":"jim-panse","email":"jim-panse-1@posteo.de"}],"homepage":"https://github.com/Jim-Panse/PDF-to-TXT-MCP#readme","bugs":{"url":"https://github.com/Jim-Panse/PDF-to-TXT-MCP/issues"},"bin":{"pdf-to-text-mcp":"dist/index.js"},"dist":{"shasum":"914a4438bf61f02b501706541532a4b8672672c9","tarball":"https://registry.npmjs.org/@jim-panse/pdf-to-text-mcp/-/pdf-to-text-mcp-0.4.4.tgz","fileCount":6,"integrity":"sha512-mgMDLrq+4EcsAQMqTES/vb5psjZ3y/F6i+WfQkF/op6V7ASWES8MCmEMZhiNW2W5MbStQhkstrYZHRBs9idJiw==","signatures":[{"sig":"MEUCIQCrF/I0WwhvsjlpPeEZ0CRwsMjq+jDTlNlNT/mgGD5glQIgDrnoT/gE8TngDoOmMoMbyXn+mXrafi6CX/+WpZd1Y84=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEUCIA9Sg7eKak8ZsHSYBYootu6lb/51BthONrEjsuVRmn/6AiEAsb7cw0RPSNwaa0IIKIXGl4gWmjogOHOtB7wplmJalTk=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":78043},"type":"module","_from":"file:jim-panse-pdf-to-text-mcp-0.4.4.tgz","engines":{"node":">=22.13.0"},"mcpName":"io.github.Jim-Panse/pdf-to-text","scripts":{"dev":"tsx watch src/index.ts","test":"vitest run","build":"tsc -p tsconfig.json --noEmit && node scripts/build.mjs","start":"node dist/index.js","prepack":"npm run build"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"4ff760c3-5a7c-4c68-ab04-79e53e0d945e"}},"_resolved":"/Users/runner/work/PDF-to-TXT-MCP/PDF-to-TXT-MCP/jim-panse-pdf-to-text-mcp-0.4.4.tgz","_integrity":"sha512-mgMDLrq+4EcsAQMqTES/vb5psjZ3y/F6i+WfQkF/op6V7ASWES8MCmEMZhiNW2W5MbStQhkstrYZHRBs9idJiw==","repository":{"url":"git+https://github.com/Jim-Panse/PDF-to-TXT-MCP.git","type":"git"},"_npmVersion":"11.21.0","description":"MCP server for extracting text from PDF files.","directories":{},"_nodeVersion":"22.23.2","dependencies":{"zod":"^4.4.3","openai":"^6.45.0","pdfjs-dist":"^6.0.227","@modelcontextprotocol/sdk":"^1.29.0"},"publishConfig":{"access":"public","registry":"https://registry.npmjs.org/"},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.20.6","terser":"^5.51.2","vitest":"^5.0.3","esbuild":"^0.28.1","typescript":"^5.9.3","@types/node":"^25.3.0"},"_npmOperationalInternal":{"tmp":"tmp/pdf-to-text-mcp_0.4.4_1791726236862_0.16224905700313141","host":"s3://npm-registry-packages-npm-production"}},"0.4.5":{"name":"@jim-panse/pdf-to-text-mcp","version":"0.4.5","keywords":["pdf","text-extraction","ocr","mcp","model-context-protocol"],"license":"AGPL-3.0-only","_id":"@jim-panse/pdf-to-text-mcp@0.4.5","maintainers":[{"name":"jim-panse","email":"jim-panse-1@posteo.de"}],"homepage":"https://github.com/Jim-Panse/PDF-to-TXT-MCP#readme","bugs":{"url":"https://github.com/Jim-Panse/PDF-to-TXT-MCP/issues"},"bin":{"pdf-to-text-mcp":"dist/index.js"},"dist":{"shasum":"4cb8b5e525b4bfe9e037c51d94586b9b60918052","tarball":"https://registry.npmjs.org/@jim-panse/pdf-to-text-mcp/-/pdf-to-text-mcp-0.4.5.tgz","fileCount":6,"integrity":"sha512-2QvqGHbw8dAA0YTn4V9I0bgzzmnJBil8sTPhe1pvt+Zi1zfmXttbvIldT3I5vctNeGObYQmTqRwqSF74F+IjBw==","signatures":[{"sig":"MEQCIByC5fCNxGLUTNaweVnaCydISuPnH49tyaeXtBenbLR/AiBVxV3KADLtG7cPQrBQJ7zb7MI+9JtidnZoa6dnLQKYiQ==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEYCIQCq93Aiq7Qt8I19VcclnHLWaXpESpm7gB2yAKOu8pLq4wIhAK1lFsdNX16n63zmMGOJ+G0IhV/EUDj1u3wLG6amlead","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":81547},"type":"module","_from":"file:jim-panse-pdf-to-text-mcp-0.4.5.tgz","engines":{"node":">=22.13.0"},"mcpName":"io.github.Jim-Panse/pdf-to-text","scripts":{"dev":"tsx watch src/index.ts","test":"vitest run","build":"tsc -p tsconfig.json --noEmit && node scripts/build.mjs","start":"node dist/index.js","prepack":"npm run build"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"4ff760c3-5a7c-4c68-ab04-79e53e0d945e"}},"_resolved":"/Users/runner/work/PDF-to-TXT-MCP/PDF-to-TXT-MCP/jim-panse-pdf-to-text-mcp-0.4.5.tgz","_integrity":"sha512-2QvqGHbw8dAA0YTn4V9I0bgzzmnJBil8sTPhe1pvt+Zi1zfmXttbvIldT3I5vctNeGObYQmTqRwqSF74F+IjBw==","repository":{"url":"git+https://github.com/Jim-Panse/PDF-to-TXT-MCP.git","type":"git"},"_npmVersion":"11.21.0","description":"MCP server for extracting text from PDF files.","directories":{},"_nodeVersion":"22.23.2","dependencies":{"zod":"^4.4.3","openai":"^6.45.0","pdfjs-dist":"^6.0.227","@modelcontextprotocol/sdk":"^1.29.0"},"publishConfig":{"access":"public","registry":"https://registry.npmjs.org/"},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.20.6","terser":"^5.51.2","vitest":"^5.0.3","esbuild":"^0.28.1","typescript":"^5.9.3","@types/node":"^25.3.0"},"_npmOperationalInternal":{"tmp":"tmp/pdf-to-text-mcp_0.4.5_1791808524383_0.5566492915778876","host":"s3://npm-registry-packages-npm-production"}},"0.5.0":{"name":"@jim-panse/pdf-to-text-mcp","version":"0.5.0","keywords":["pdf","text-extraction","ocr","mcp","model-context-protocol"],"license":"AGPL-3.0-only","_id":"@jim-panse/pdf-to-text-mcp@0.5.0","maintainers":[{"name":"jim-panse","email":"jim-panse-1@posteo.de"}],"homepage":"https://github.com/Jim-Panse/PDF-to-TXT-MCP#readme","bugs":{"url":"https://github.com/Jim-Panse/PDF-to-TXT-MCP/issues"},"bin":{"pdf-to-text-mcp":"dist/index.js"},"dist":{"shasum":"02e1ee4d4f5ea4f587cffa04ba12a113f47e6f2d","tarball":"https://registry.npmjs.org/@jim-panse/pdf-to-text-mcp/-/pdf-to-text-mcp-0.5.0.tgz","fileCount":6,"integrity":"sha512-y72DOASO/VR7GBK7fgnZAgzki5nHXXCBXWidwpHaeYS+B5Bttuom7tvJzWIEOe0FtPzfe3MaaLX/A3lKWWWsLA==","signatures":[{"sig":"MEQCIAtk+0x6f0x/08DzSc7azDPvGt86GaNpuKobB8cO+NkbAiABFgWLlFzhm7/ZXaaFYySuwjy9xd/XTREqY+hMLDZccQ==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEYCIQDsiMAqk/PVNNElTtHMkz5JEKLnuPNW1PHzNcqIxz9JVgIhAKBkVmKgv3HAskQmtMEm6aTlq3yzUcLh+9sG48yM16Pk","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":86214},"type":"module","_from":"file:jim-panse-pdf-to-text-mcp-0.5.0.tgz","engines":{"node":">=22.13.0"},"mcpName":"io.github.Jim-Panse/pdf-to-text","scripts":{"dev":"tsx watch src/index.ts","test":"vitest run","build":"tsc -p tsconfig.json --noEmit && node scripts/build.mjs","start":"node dist/index.js","prepack":"npm run build"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"4ff760c3-5a7c-4c68-ab04-79e53e0d945e"}},"_resolved":"/Users/runner/work/PDF-to-TXT-MCP/PDF-to-TXT-MCP/jim-panse-pdf-to-text-mcp-0.5.0.tgz","_integrity":"sha512-y72DOASO/VR7GBK7fgnZAgzki5nHXXCBXWidwpHaeYS+B5Bttuom7tvJzWIEOe0FtPzfe3MaaLX/A3lKWWWsLA==","repository":{"url":"git+https://github.com/Jim-Panse/PDF-to-TXT-MCP.git","type":"git"},"_npmVersion":"11.21.0","description":"MCP server for extracting text from PDF files.","directories":{},"_nodeVersion":"22.23.2","dependencies":{"zod":"^4.4.3","openai":"^6.45.0","pdfjs-dist":"^6.0.227","@modelcontextprotocol/sdk":"^1.29.0"},"publishConfig":{"access":"public","registry":"https://registry.npmjs.org/"},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.20.6","terser":"^5.51.2","vitest":"^5.0.3","esbuild":"^0.28.1","typescript":"^5.9.3","@types/node":"^25.3.0"},"_npmOperationalInternal":{"tmp":"tmp/pdf-to-text-mcp_0.5.0_1791828041242_0.7897675888764892","host":"s3://npm-registry-packages-npm-production"}},"0.6.0":{"name":"@jim-panse/pdf-to-text-mcp","version":"0.6.0","keywords":["pdf","text-extraction","ocr","mcp","model-context-protocol"],"license":"AGPL-3.0-only","_id":"@jim-panse/pdf-to-text-mcp@0.6.0","maintainers":[{"name":"jim-panse","email":"jim-panse-1@posteo.de"}],"homepage":"https://github.com/Jim-Panse/PDF-to-TXT-MCP#readme","bugs":{"url":"https://github.com/Jim-Panse/PDF-to-TXT-MCP/issues"},"bin":{"pdf-to-text-mcp":"dist/index.js"},"dist":{"shasum":"acf98d88ec76223e6af08c1c47c5ad4d75420d08","tarball":"https://registry.npmjs.org/@jim-panse/pdf-to-text-mcp/-/pdf-to-text-mcp-0.6.0.tgz","fileCount":6,"integrity":"sha512-A/mImlDmQZfGFDcU8fnKIn18hFudapjzqwa1Rfs+lqE7SgGyLI+FmOWxy9hZdijNvoLVnnm3kaCFSZ743UyaHA==","signatures":[{"sig":"MEYCIQCF2VkRBMMY2lGB58OscR4XyjHM1ZxKTopEB1oXx6ESQAIhAKU/Ao3qOYZV1yDH7cF4eKWr/Hyo+diWEEoXzmHywfHU","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEQCIAVaen+lDEd6jLt7LT6TFuBrxktirswGwJRB0vjTMbgeAiBK+YcJExpktbYhhIbYzeRwkod9/cqSsKNuL3HXhwXWxA==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":94923},"type":"module","_from":"file:jim-panse-pdf-to-text-mcp-0.6.0.tgz","engines":{"node":">=22.13.0"},"mcpName":"io.github.Jim-Panse/pdf-to-text","scripts":{"dev":"tsx watch src/index.ts","test":"vitest run","build":"tsc -p tsconfig.json --noEmit && node scripts/build.mjs","start":"node dist/index.js","prepack":"npm run build"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"4ff760c3-5a7c-4c68-ab04-79e53e0d945e"}},"_resolved":"/Users/runner/work/PDF-to-TXT-MCP/PDF-to-TXT-MCP/jim-panse-pdf-to-text-mcp-0.6.0.tgz","_integrity":"sha512-A/mImlDmQZfGFDcU8fnKIn18hFudapjzqwa1Rfs+lqE7SgGyLI+FmOWxy9hZdijNvoLVnnm3kaCFSZ743UyaHA==","repository":{"url":"git+https://github.com/Jim-Panse/PDF-to-TXT-MCP.git","type":"git"},"_npmVersion":"11.21.0","description":"MCP server for extracting text from PDF files.","directories":{},"_nodeVersion":"22.23.2","dependencies":{"zod":"^4.4.3","openai":"^6.45.0","pdfjs-dist":"^6.0.227","@modelcontextprotocol/sdk":"^1.29.0"},"publishConfig":{"access":"public","registry":"https://registry.npmjs.org/"},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.20.6","terser":"^5.51.2","vitest":"^5.0.3","esbuild":"^0.28.1","typescript":"^5.9.3","@types/node":"^25.3.0"},"_npmOperationalInternal":{"tmp":"tmp/pdf-to-text-mcp_0.6.0_1792054357611_0.8446733693673307","host":"s3://npm-registry-packages-npm-production"}},"0.7.0":{"_id":"@jim-panse/pdf-to-text-mcp@0.7.0","bin":{"pdf-to-text-mcp":"dist/index.js"},"bugs":{"url":"https://github.com/Jim-Panse/PDF-to-TXT-MCP/issues"},"dist":{"shasum":"24f8832dd9000e6ca4194491c8fa06e9984ef235","tarball":"https://registry.npmjs.org/@jim-panse/pdf-to-text-mcp/-/pdf-to-text-mcp-0.7.0.tgz","fileCount":9,"integrity":"sha512-1ej6r+BsAy+2M1+Zo43sq6jbQzpcYHJB2llNDZOPQUWnDx0GtaC/kOHRZvPR1R9FIM48a+MPjWD7h9laPN+96A==","signatures":[{"sig":"MEYCIQDW+qe/j/IAPAHr+ppW/A7XSa4/HrceknHkouGdIF+I6AIhAN10alRI0iK3oQCSqPFlg1wNXLaVJ+XCCrlGoKgDk3sB","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEQCIDT2oxiTwIL3joGyIVctl54InKRdZa3/KaQH4SeLVqeuAiBcI7TeIcHJEQSWo4euaw8GtgjEJQb8wmhn5qxiJUaXcA=="}],"unpackedSize":117775},"name":"@jim-panse/pdf-to-text-mcp","type":"module","_from":"file:jim-panse-pdf-to-text-mcp-0.7.0.tgz","engines":{"node":">=22.13.0"},"license":"AGPL-3.0-only","mcpName":"io.github.Jim-Panse/pdf-to-text","scripts":{"dev":"tsx watch src/index.ts","test":"vitest run","build":"tsc -p tsconfig.json --noEmit && node scripts/build.mjs","start":"node dist/index.js","prepack":"npm run build"},"version":"0.7.0","_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"4ff760c3-5a7c-4c68-ab04-79e53e0d945e"}},"homepage":"https://github.com/Jim-Panse/PDF-to-TXT-MCP#readme","keywords":["pdf","text-extraction","ocr","mcp","model-context-protocol"],"_resolved":"/Users/runner/work/PDF-to-TXT-MCP/PDF-to-TXT-MCP/jim-panse-pdf-to-text-mcp-0.7.0.tgz","_integrity":"sha512-1ej6r+BsAy+2M1+Zo43sq6jbQzpcYHJB2llNDZOPQUWnDx0GtaC/kOHRZvPR1R9FIM48a+MPjWD7h9laPN+96A==","repository":{"url":"git+https://github.com/Jim-Panse/PDF-to-TXT-MCP.git","type":"git"},"_npmVersion":"11.21.0","description":"MCP server for extracting text from PDF files.","directories":{},"maintainers":[{"name":"jim-panse","email":"jim-panse-1@posteo.de"}],"_nodeVersion":"22.23.2","dependencies":{"zod":"^4.4.3","openai":"^6.45.0","pdfjs-dist":"^6.0.227","@modelcontextprotocol/sdk":"^1.29.0"},"publishConfig":{"access":"public","registry":"https://registry.npmjs.org/"},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.20.6","terser":"^5.51.2","vitest":"^5.0.3","esbuild":"^0.28.1","typescript":"^5.9.3","@types/node":"^25.3.0"},"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/pdf-to-text-mcp_0.7.0_1792066530626_0.2703125604866916"}}},"time":{"created":"2026-10-10T13:26:15.263Z","modified":"2026-10-15T12:15:30.922Z","0.0.0-stage":"2026-10-10T13:26:15.263Z","0.4.1":"2026-10-10T13:27:56.895Z","0.4.2":"2026-10-10T13:54:12.074Z","0.4.3":"2026-10-10T14:04:34.457Z","0.4.4":"2026-10-11T13:43:56.963Z","0.4.5":"2026-10-12T12:35:24.466Z","0.5.0":"2026-10-12T18:00:41.336Z","0.6.0":"2026-10-15T08:52:37.708Z","0.7.0":"2026-10-15T12:15:30.735Z"},"bugs":{"url":"https://github.com/Jim-Panse/PDF-to-TXT-MCP/issues"},"license":"AGPL-3.0-only","homepage":"https://github.com/Jim-Panse/PDF-to-TXT-MCP#readme","keywords":["pdf","text-extraction","ocr","mcp","model-context-protocol"],"repository":{"url":"git+https://github.com/Jim-Panse/PDF-to-TXT-MCP.git","type":"git"},"description":"MCP server for extracting text from PDF files.","maintainers":[{"name":"jim-panse","email":"jim-panse-1@posteo.de"}],"readme":"# PDF To Text MCP\n\n[Deutsche Dokumentation](./LIES_MICH.md)\n\n[Changelog](./CHANGELOG.md)\n\nA local MCP server that extracts text from PDF files. It starts with local\nextraction and can upgrade an inadequate result once through the OpenAI API.\nPackage version: `0.7.0`.\n\n## Requirements\n\n- Node.js 22.13 or newer\n- An MCP client that supports local stdio servers\n- macOS for the optional local PDFKit and Vision OCR fallbacks; the normal\n  local extractor uses `pdfjs-dist` on every supported Node.js platform\n- `OPENAI_API_KEY` only when AI fallback should be available\n\nSet the required `PDF_TO_TEXT_MCP_ROOT` environment variable to an existing\ndirectory. Tool paths are relative to that root, and the process still needs\nmatching runtime read or write permissions. The configured root is private to\nthe server and never appears in tool arguments or results.\n\n## Dependencies and limitations at a glance\n\n| Capability | Requirement | Platform | Current limitation |\n| --- | --- | --- | --- |\n| Embedded PDF text | Node.js ≥ 22.13; bundled `pdfjs-dist` | Linux, macOS, Windows | No OCR; damaged font encoding and PDF object order can produce garbled text or incorrect reading order. |\n| Local PDFKit/Vision fallback | System `swift`, PDFKit, Apple Vision | macOS only | Unavailable on Linux and Windows; local OCR quality is therefore not platform-equivalent before 1.0.0. |\n| AI extraction retry | `OPENAI_API_KEY`, network access | Any supported Node.js platform | At most one retry per attempt; generated output can be wrong and may incur provider costs. |\n| Save extracted text | `WRITE_TEXT=true`, directory write permission, hard-link support | Filesystem-dependent | Existing targets are never overwritten; `PDF_TO_TEXT_MCP_ROOT` is required and paths are root-relative. Complete TOCTOU hardening remains a separate task. |\n\n## File access and request behavior\n\n| Operation | Behavior |\n| --- | --- |\n| Read source PDF | Yes; through a path relative to `PDF_TO_TEXT_MCP_ROOT`. The source remains unchanged. |\n| Modify or delete source PDF | Never. |\n| Write extracted text | Only with `WRITE_TEXT=true`; writes the exact returned text beside the source as `document.pdf.txt`. The actual root-relative path is returned as `saved_text_path` only after writing succeeds. |\n| Overwrite existing output | Never; final publication also rejects a target created after the initial availability check. |\n| Target name already exists | Fail with an error. No suffixed name is chosen; resolve the conflict outside the tool. |\n| Repeat without `last_try_id` | Start a new local extraction. With text saving enabled, an existing output blocks the call. |\n| Repeat a completed AI attempt | Reuse the retained result for the same unchanged source and page scope, without another AI extraction. Output collision rules still apply. |\n| Request while another extraction runs | Run within the concurrency limit or wait in the bounded FIFO queue; reject when full or expired. |\n| Retain attempt results | In the AI-enabled profile, retain up to ten completed attempts in FIFO order. Evicted IDs fail explicitly. Any number of PDFs can be extracted sequentially. |\n| Send PDF to an external provider | Only on an explicit AI continuation with `OPENAI_API_KEY` configured. The complete PDF is sent to OpenAI, even when `page_range` selects only part of its text. |\n\n## Install and connect\n\nRun the server directly from npm:\n\n```bash\nnpx -y @jim-panse/pdf-to-text-mcp\n```\n\nOr install its executable globally:\n\n```bash\nnpm install --global @jim-panse/pdf-to-text-mcp\npdf-to-text-mcp\n```\n\nFor example, register it with Codex using:\n\n```bash\ncodex mcp add pdf-to-text -- npx -y @jim-panse/pdf-to-text-mcp\n```\n\nThe server also needs `PDF_TO_TEXT_MCP_ROOT` in its MCP process environment.\nThe JSON example below shows that setting; configure the same variable in the\nclient's server environment when using the CLI registration.\n\nEquivalent JSON-based MCP clients can use:\n\n```json\n{\n  \"mcpServers\": {\n    \"pdf-to-text\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@jim-panse/pdf-to-text-mcp\"],\n      \"env\": { \"PDF_TO_TEXT_MCP_ROOT\": \"/path/to/pdf-library\" }\n    }\n  }\n}\n```\n\nThe server communicates through standard input/output. Diagnostic logs go to\nstandard error and do not interfere with MCP messages.\n\n## First extraction\n\nCall `extraction-try` with a root-relative PDF path:\n\n```json\n{ \"path\": \"document.pdf\" }\n```\n\nThe first call extracts locally. AI continuation is available only when configured\nand explicitly requested. The complete PDF is sent on AI continuation even if\n`page_range` limits the requested text. Sources and existing outputs are never\noverwritten. Requests overlap asynchronously without a JavaScript worker pool.\nA client timeout does not stop admitted work; avoid automatic retries.\n\n## Configuration at a glance\n\nSet variables in the MCP server's environment:\n\n| Variable | Meaning |\n| --- | --- |\n| `PDF_TO_TEXT_MCP_ROOT` | Required existing directory defining the root-relative filesystem namespace. The server does not fall back to its working directory. |\n| `OPENAI_API_KEY` | Enables the optional one-time AI fallback. Local extraction works without it. |\n| `OPENAI_MODEL` | Overrides the AI model. The default is `gpt-5.4-mini`. |\n| `AI_MAX_OUTPUT_TOKENS` | Upper limit for AI-generated output tokens. Must be an integer of at least `800`; defaults to `32000`. |\n| `WRITE_TEXT` | `true` saves each successful result beside the PDF; `false` or omission disables saving. |\n| `MAX_PARALLEL_EXTRACTIONS` | Integer from `1` to `32`; defaults to `min(os.availableParallelism(), 4)`. |\n| `EXTRACTION_QUEUE_CAPACITY` | Integer from `0` to `100`; defaults to `10`; `0` disables waiting. |\n| `EXTRACTION_QUEUE_WAIT_MS` | Integer from `1` to `2147483647`; defaults to `60000` ms; applies only before execution. |\n\nDetailed behavior, diagrams, queue examples, timeout consequences and\ntroubleshooting are in the [user manual](docs/usage.md).\nCalling models should follow [Model interaction](docs/model-interaction.md).\n\n## Support\n\nNo free support is provided for this free software. Paid support is available\non request: [jim-panse-1@posteo.de](mailto:jim-panse-1@posteo.de).\n\n## Third-party directories\n\n- [MCPRush listing](https://mcprush.com/jim-panse/pdf-to-text-mcp)\n- [npm.io package listing](https://npm.io/package/%40jim-panse/pdf-to-text-mcp)\n\nThese independent directories may show outdated package metadata. For current\nproduct and release information, use the [included user manual](docs/usage.md)\nand the [official npm package](https://www.npmjs.com/package/@jim-panse/pdf-to-text-mcp).\n\nLicense: AGPL-3.0-only.\n","readmeFilename":"README.md"}