{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_9stvxe3nrvym","handle":"document-intelligence-mcp","url":"https://wellknown.network/agents/document-intelligence-mcp","links":{"self":"https://wellknown.network/agents/document-intelligence-mcp/record.json","html":"https://wellknown.network/agents/document-intelligence-mcp","markdown":"https://wellknown.network/agents/document-intelligence-mcp/record.md","api":"https://wellknown.network/api/v1/agents/document-intelligence-mcp","status":"https://wellknown.network/api/v1/agents/document-intelligence-mcp/status","claim":"https://wellknown.network/agents/document-intelligence-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/document-intelligence-mcp/claim.json","badge":"https://wellknown.network/agents/document-intelligence-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/document-intelligence-mcp/history","tools":"https://wellknown.network/api/v1/agents/document-intelligence-mcp/tools"},"ard":{"identifier":"urn:air::server:document-intelligence-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"document-intelligence-mcp","summary":"MCP Server for local document analysis: PDF text extraction, table detection, DOCX parsing, language detection and keyword search — no cloud API required","description":"# document-intelligence-mcp\n\n[![PyPI version](https://badge.fury.io/py/document-intelligence-mcp.svg)](https://badge.fury.io/py/document-intelligence-mcp)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)\n\n**Local document intelligence for AI agents** — extract text, detect tables, read metadata, analyze structure, search keywords, and detect language from PDF and DOCX files. No cloud API required, no API key needed.\n\n## Features\n\n- **10 MCP Tools** for PDF and DOCX processing\n- **Local processing** — no data leaves your machine\n- **No API key** required\n- Supports **PDF** (via PyMuPDF + pdfplumber) and **Microsoft Word DOCX** (via python-docx)\n- Language detection via langdetect (55+ languages)\n\n## Tools\n\n| Tool | Description |\n|------|-------------|\n| `tool_extract_text_from_pdf` | Extract all text from a PDF, page by page |\n| `tool_extract_tables_from_pdf` | Detect and extract tables from PDF |\n| `tool_get_pdf_metadata` | Read PDF metadata: title, author, dates, outline |\n| `tool_analyze_document_structure` | Detect headings, font sizes, section structure |\n| `tool_search_in_pdf` | Search for keywords with context in PDF |\n| `tool_extract_text_from_docx` | Extract all text from a Word DOCX file |\n| `tool_extract_tables_from_docx` | Extract all tables from a DOCX file |\n| `tool_analyze_docx_structure` | Analyze headings, styles, and structure of DOCX |\n| `tool_count_words_and_stats` | Word count, sentence count, reading time, top words |\n| `tool_detect_document_language` | Detect language of PDF or DOCX (55+ languages) |\n\n## Installation\n\n```bash\npip install document-intelligence-mcp\n```\n\n## Claude Desktop Configuration\n\nAdd to your `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"document-intelligence\": {\n      \"command\": \"document-intelligence-mcp\"\n    }\n  }\n}\n```\n\n## Usage Examples\n\n**…","publisher":null,"homepage":"https://github.com/AiAgentKarl/document-intelligence-mcp","repository":"https://github.com/AiAgentKarl/document-intelligence-mcp","version":"0.1.0","license":"MIT","protocols":["mcp"],"tags":["ai-agent","document","document-intelligence","docx","mcp","pdf","text-extraction"],"pricing":null,"endpoints":[{"url":"pypi:document-intelligence-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"documents.extraction","name":"Data Extraction","confidence":1,"provenance":"derived"},{"slug":"documents.conversion","name":"Document Conversion","confidence":1,"provenance":"declared"}],"categories":["documents"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"document-intelligence-mcp","registry":"pypi","observedAt":"2026-10-27T23:25:38.545Z","publishedAt":"2026-04-16T10:12:29.309757Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"document-intelligence-mcp","url":"https://pypi.org/project/document-intelligence-mcp/","firstSeenAt":"2026-09-09T14:32:04.789Z","fetchedAt":"2026-10-27T23:24:53.703Z","normalizedAt":"2026-10-27T23:24:53.703Z"}]},"firstSeenAt":"2026-09-09T14:32:04.789Z","updatedAt":"2026-10-27T23:25:38.545Z"}