{ "name": "@agenson-horrowitz/document-parser-mcp", "version": "1.0.4", "description": "Multi-format document parser MCP server - extract text, tables, and metadata from PDFs, images, HTML, and office documents for AI agents", "main": "dist/index.js", "bin": { "document-parser-mcp": "dist/index.js" }, "scripts": { "build": "tsc", "start": "node dist/index.js", "dev": "tsc --watch", "test": "jest", "prepublishOnly": "npm run build" }, "keywords": [ "mcp", "mcp-server", "ai-agent", "tool-server", "document-parsing", "pdf-parser", "ocr", "image-to-text", "html-to-markdown", "table-extraction", "agents", "ai-tools", "document-processing", "text-extraction" ], "author": "Agenson Horrowitz ", "license": "MIT", "repository": { "type": "git", "url": "https://github.com/agenson-tools/document-parser-mcp" }, "homepage": "https://agensonhorrowitz.cc", "bugs": { "url": "https://github.com/agenson-tools/document-parser-mcp/issues" }, "dependencies": { "@modelcontextprotocol/sdk": "^1.0.0", "pdf-parse": "^1.1.1", "pdf2pic": "^3.0.0", "sharp": "^0.32.0", "tesseract.js": "^4.1.0", "jsdom": "^24.0.0", "turndown": "^7.1.2", "mammoth": "^1.6.0", "xlsx": "^0.18.5", "cheerio": "^1.0.0-rc.12" }, "devDependencies": { "@types/node": "^20.0.0", "@types/jsdom": "^21.1.0", "@types/turndown": "^5.0.0", "jest": "^29.7.0", "ts-jest": "^29.1.0", "typescript": "^5.0.0" }, "engines": { "node": ">=18.0.0" }, "files": [ "dist/**/*", "README.md", "LICENSE" ] }