{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_p4cacsrw4cmk","handle":"mcp-pdf-2","url":"https://wellknown.network/agents/mcp-pdf-2","links":{"self":"https://wellknown.network/agents/mcp-pdf-2/record.json","html":"https://wellknown.network/agents/mcp-pdf-2","markdown":"https://wellknown.network/agents/mcp-pdf-2/record.md","api":"https://wellknown.network/api/v1/agents/mcp-pdf-2","status":"https://wellknown.network/api/v1/agents/mcp-pdf-2/status","claim":"https://wellknown.network/agents/mcp-pdf-2/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-pdf-2/claim.json","badge":"https://wellknown.network/agents/mcp-pdf-2/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-pdf-2/history","tools":"https://wellknown.network/api/v1/agents/mcp-pdf-2/tools"},"ard":{"identifier":"urn:air::server:mcp-pdf-2","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-pdf","summary":"Secure FastMCP server for comprehensive PDF processing - text extraction, OCR, table extraction, forms, annotations, and more","description":"<div align=\"center\">\n\n# 📄 MCP PDF\n\n<img src=\"https://img.shields.io/badge/MCP-PDF%20Tools-red?style=for-the-badge&logo=adobe-acrobat-reader\" alt=\"MCP PDF\">\n\n**A FastMCP server for PDF processing**\n\n*52 tools for text extraction, OCR, tables, forms, XFA, annotations, markdown↔PDF, and more*\n\n[![Python 3.11+](https://img.shields.io/badge/python-3.11+-blue.svg?style=flat-square)](https://www.python.org/downloads/)\n[![FastMCP](https://img.shields.io/badge/FastMCP-2.0+-green.svg?style=flat-square)](https://github.com/jlowin/fastmcp)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg?style=flat-square)](https://opensource.org/licenses/MIT)\n[![PyPI](https://img.shields.io/pypi/v/mcp-pdf?style=flat-square)](https://pypi.org/project/mcp-pdf/)\n\n**Works great with [MCP Office Tools](https://git.supported.systems/MCP/mcp-office-tools)**\n\n</div>\n\n---\n\n## What It Does\n\nMCP PDF extracts content from PDFs using multiple libraries with automatic fallbacks. If one method fails, it tries another.\n\n**Core capabilities:**\n- **Text extraction** via PyMuPDF, pdfplumber, or pypdf (auto-fallback)\n- **Table extraction** via Camelot, pdfplumber, or Tabula (auto-fallback)\n- **OCR** for scanned documents via Tesseract\n- **Form handling** - extract, fill, and create PDF forms\n- **Document assembly** - merge, split, reorder pages\n- **Annotations** - sticky notes, highlights, stamps\n- **Vector graphics** - extract to SVG for schematics and technical drawings\n- **Format conversion** - PDF ↔ Markdown (PDF→MD via PyMuPDF, MD→PDF via pandoc)\n- **XFA forms** - Schema extraction for dynamic Adobe LiveCycle forms that no open-source library can render\n\n---\n\n## Quick Start\n\n```bash\n# Run from PyPI (one-shot, no permanent install)\nuvx mcp-pdf\n\n# Add to Claude Code — note the `--` separator before uvx\nclaude mcp add pdf-tools -- uvx mcp-pdf\n\n# Include the markdown_to_pdf tool (requires pandoc on host)\nclaude mcp add pdf-tools -- uvx --from \"mcp-pdf[markdown]\" mcp-pdf\n```\n\n> `uvx` caches …","publisher":null,"homepage":"https://github.com/rsp2k/mcp-pdf#readme","repository":"https://github.com/rsp2k/mcp-pdf/blob/main/CHANGELOG.md","version":"2026.9.22","license":"MIT","protocols":["mcp"],"tags":["api","fastmcp","integration","mcp","ocr","pdf","pdf-processing","table-extraction","text-extraction"],"pricing":null,"endpoints":[{"url":"pypi:mcp-pdf","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.ocr","name":"OCR","confidence":1,"provenance":"declared"},{"slug":"documents.extraction","name":"Data Extraction","confidence":1,"provenance":"derived"},{"slug":"documents.conversion","name":"Document Conversion","confidence":1,"provenance":"derived"},{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.791,"provenance":"derived"},{"slug":"dev.version-control","name":"Version Control","confidence":0.745,"provenance":"derived"}],"categories":["dev","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":"mcp-pdf","registry":"pypi","observedAt":"2026-10-28T12:23:00.613Z","publishedAt":"2026-09-22T08:18:33.439207Z","latestVersion":"2026.9.22"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-pdf","url":"https://pypi.org/project/mcp-pdf/","firstSeenAt":"2026-09-10T02:24:40.973Z","fetchedAt":"2026-10-28T12:21:50.588Z","normalizedAt":"2026-10-28T12:21:50.588Z"}]},"firstSeenAt":"2026-09-10T02:24:40.973Z","updatedAt":"2026-10-28T12:23:00.614Z"}