{"name":"io.github.agenson-horrowitz/document-parser","slug":"agenson-horrowitz-document-parser","title":null,"description":"Parse and extract structured data from various document formats (PDF, Word, HTML).","url":"https://mcp.market/server/agenson-horrowitz-document-parser","rating":null,"grade":"B","score":75,"certified":false,"status":"active","category":"scraping","tags":["scraping"],"presence":{"score":15,"stars":0,"forks":1,"downloads_week":57,"last_push_at":"2026-04-02T12:31:36.000Z","license":"MIT"},"uptime":null,"claimed":false,"transport":"npm","callable_via_gateway":false,"default_price_micros":0,"repository":"https://github.com/agenson-tools/document-parser-mcp","website":null,"version":"1.0.8","remotes":[],"packages":[{"registryType":"npm","identifier":"@agenson-horrowitz/document-parser-mcp","version":"1.0.8","transport":{"type":"stdio"}}],"tools":[{"name":"extract_tables","description":"Extract tables from any supported document format as structured JSON. Handles PDF tables, HTML tables, CSV-like structures in text. Returns clean tabular data perfect for agent analysis and processing.","write_action":false,"price_micros":0,"input_schema":null},{"name":"html_to_markdown","description":"Convert HTML documents to clean, structured markdown. Preserves headings, links, tables, lists. Perfect for agents that need to process HTML content in LLM-friendly format. Handles complex HTML structures intelligently.","write_action":false,"price_micros":0,"input_schema":null},{"name":"parse_image_text","description":"Perform OCR on images to extract text with confidence scores. Supports screenshots, scanned documents, photos of text. Returns structured text with confidence metrics. Essential for agents processing visual content.","write_action":false,"price_micros":0,"input_schema":null},{"name":"parse_pdf","description":"Extract text, tables, and metadata from PDF files with layout preservation. Perfect for agents processing reports, invoices, contracts, research papers. Handles multi-page documents, preserves formatting, extracts embedded metadata.","write_action":false,"price_micros":0,"input_schema":null},{"name":"summarize_document","description":"Parse any document and generate a structured summary with configurable detail level. Extracts key information, main points, and metadata. Perfect for agents that need document overviews before detailed processing.","write_action":false,"price_micros":0,"input_schema":null}],"scan":{"score":75,"grade":"B","scanned_at":"2026-09-27T23:17:44.978Z","report":{"scannerVersion":"0.1.9","scannedAt":"2026-09-27T23:17:44.914Z","components":{"code":{"score":25,"max":25,"notes":["3 source files scanned"]},"reliability":{"score":-1,"max":20,"notes":["no gateway calls yet and no remote to probe"]},"poisoning":{"score":-1,"max":15,"notes":["tools not inspected (local package is not executed); not counted"]},"auth":{"score":12,"max":15,"notes":["local package, no credentials required"]},"maintenance":{"score":8,"max":15,"notes":["last push 178 days ago"]},"identity":{"score":4,"max":10,"notes":["namespace and repository owner differ"]}},"findings":[],"inputs":{"packages":[{"registryType":"npm","identifier":"@agenson-horrowitz/document-parser-mcp","version":"1.0.8","found":true,"license":"MIT","hasInstallScripts":false,"dependencyCount":10,"publishedAt":"2026-04-02T12:26:54.476Z","repositoryUrl":"git+https://github.com/agenson-tools/document-parser-mcp.git","weeklyDownloads":57}],"repo":{"found":true,"owner":"agenson-tools","repo":"document-parser-mcp","archived":false,"pushedAt":"2026-04-02T12:31:36Z","stars":0,"forks":1,"openIssues":1,"ownerType":"Organization","ownerAvatarUrl":"https://avatars.githubusercontent.com/u/273038814?v=4","ownerCreatedAt":"2026-04-02T07:50:47Z","license":"MIT"},"icon":{"url":null,"source":"none"},"presence":{"stars":0,"forks":1,"downloadsWeek":57,"license":"MIT","lastPushAt":"2026-04-02T12:31:36.000Z","score":15}}}},"grade_history":[],"reviews":[]}