{"_id":"@allenpan2026/harshjudge-mcp","name":"@allenpan2026/harshjudge-mcp","dist-tags":{"latest":"0.3.2"},"versions":{"0.3.2":{"name":"@allenpan2026/harshjudge-mcp","version":"0.3.2","description":"AI-native E2E testing orchestration MCP server for Claude Code. Create, run, and manage end-to-end test scenarios with visual evidence capture.","type":"module","main":"./dist/index.js","types":"./dist/index.d.ts","bin":{"harshjudge-mcp":"dist/server.js"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.js"}},"scripts":{"build":"tsup","build:tsc":"tsc --build","dev":"tsc --build --watch","clean":"rm -rf dist tsconfig.tsbuildinfo","typecheck":"tsc --noEmit","lint":"eslint src --ext .ts,.tsx","test":"vitest run","start":"node ./dist/server.js","prepublishOnly":"pnpm run build"},"keywords":["mcp","model-context-protocol","claude","claude-code","e2e-testing","testing","automation","ai","anthropic"],"author":{"name":"Allen Pan","email":"therealjunchen@163.com"},"license":"MIT","mcpName":"io.github.allenpan2026/harshjudge","repository":{"type":"git","url":"git+https://github.com/HuskyDanny/HarshJudge.git","directory":"packages/mcp-server"},"homepage":"https://github.com/HuskyDanny/HarshJudge#readme","bugs":{"url":"https://github.com/HuskyDanny/HarshJudge/issues"},"engines":{"node":">=18.0.0"},"dependencies":{"@modelcontextprotocol/sdk":"^1.0.0","js-yaml":"^4.1.0","nanoid":"^5.0.9","zod":"^3.23.0"},"devDependencies":{"@harshjudge/shared":"workspace:*","@harshjudge/ux":"workspace:*","@types/js-yaml":"^4.0.9","memfs":"^4.6.0","tsup":"^8.5.1","typescript":"^5.3.0"},"_id":"@allenpan2026/harshjudge-mcp@0.3.2","gitHead":"77014953d1cf570f60b7c8f72e1b1efa1b5e0a5f","_nodeVersion":"23.7.0","_npmVersion":"11.4.2","dist":{"integrity":"sha512-60AJm9hPGca+PABEnsxv4F4WgnimIX7w9emyoFGH7KmZGEOdJ4M3YFC02AvrWnIPTsbqzG3fElWas0NVxbN4/g==","shasum":"27495296cf3f906c00c3d27e8f7c1236b58b10fc","tarball":"https://registry.npmjs.org/@allenpan2026/harshjudge-mcp/-/harshjudge-mcp-0.3.2.tgz","fileCount":12,"unpackedSize":746721,"signatures":[{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEUCIQDWap+QgbDgEOSCaO8tWt40xs3M9fi90eO/9hhY8hCU9wIgN9L/iYAlOXWwC0E2PEaDKVGly1Yy+38G1Pu4AkATgH0="}]},"_npmUser":{"name":"allenpan2026","email":"therealjunchen@163.com"},"directories":{},"maintainers":[{"name":"allenpan2026","email":"therealjunchen@163.com"}],"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/harshjudge-mcp_0.3.2_1770431537383_0.8870744312528147"},"_hasShrinkwrap":false}},"time":{"created":"2026-02-07T02:32:17.268Z","0.3.2":"2026-02-07T02:32:17.592Z","modified":"2026-02-07T02:32:17.830Z"},"maintainers":[{"name":"allenpan2026","email":"therealjunchen@163.com"}],"description":"AI-native E2E testing orchestration MCP server for Claude Code. Create, run, and manage end-to-end test scenarios with visual evidence capture.","homepage":"https://github.com/HuskyDanny/HarshJudge#readme","keywords":["mcp","model-context-protocol","claude","claude-code","e2e-testing","testing","automation","ai","anthropic"],"repository":{"type":"git","url":"git+https://github.com/HuskyDanny/HarshJudge.git","directory":"packages/mcp-server"},"author":{"name":"Allen Pan","email":"therealjunchen@163.com"},"bugs":{"url":"https://github.com/HuskyDanny/HarshJudge/issues"},"license":"MIT","readme":"# @allenpan/harshjudge-mcp\n\nAI-native E2E testing orchestration MCP server for Claude Code.\n\n## Installation\n\n```bash\nnpm install -g @allenpan/harshjudge-mcp\n```\n\nOr use with npx:\n\n```bash\nnpx @allenpan/harshjudge-mcp\n```\n\n## Claude Code Configuration\n\nAdd to your Claude Code MCP settings:\n\n```json\n{\n  \"mcpServers\": {\n    \"harshjudge\": {\n      \"command\": \"npx\",\n      \"args\": [\"@allenpan/harshjudge-mcp\"]\n    },\n    \"playwright\": {\n      \"command\": \"npx\",\n      \"args\": [\"@anthropic/playwright-mcp-server\"]\n    }\n  }\n}\n```\n\n## MCP Tools\n\n| Tool | Purpose |\n|------|---------|\n| `initProject` | Initialize HarshJudge in your project |\n| `saveScenario` | Save a test scenario |\n| `startRun` | Start a new test run |\n| `recordEvidence` | Record test evidence |\n| `completeRun` | Complete a test run |\n| `getStatus` | Get project/scenario status |\n| `openDashboard` | Start dashboard UI |\n| `closeDashboard` | Stop dashboard |\n| `getDashboardStatus` | Check dashboard status |\n\n## Usage\n\n```bash\n# In Claude Code\n> Initialize HarshJudge in this project\n> Create a login test scenario\n> Run the login-flow scenario\n```\n\n## Documentation\n\n- [Full documentation](https://github.com/HuskyDanny/HarshJudge)\n- [Claude Code Skills](https://github.com/HuskyDanny/HarshJudge/tree/main/skills/harshjudge)\n\n## License\n\nMIT\n","readmeFilename":"README.md","_rev":"1-03992a10ccfdb7700b897215fa487f17"}