pdf-mcp

jztan/pdf-mcp

★ 57 stars Python AI/LLM Updated today

MCP server that lets Claude Code and other AI agents read large PDFs without hitting context limits. Chunked reading, hybrid search, OCR, table and image extraction, SQLite cache.

View on GitHub → Try with Claude — $10 free →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "pdf-mcp": {
      "command": "uvx",
      "args": [
        "pdf-mcp"
      ]
    }
  }
}

Or install with pip: pip install pdf-mcp

README Excerpt

**Surgical PDF access for AI agents — search, read, and extract without flooding context.** A [Model Context Protocol](https://modelcontextprotocol.io/) (MCP) server that enables AI agents to read, search, and extract content from PDF files. Built with Python and PyMuPDF, with SQLite-based caching for persistence across server restarts.

Tools (9)

pdf_cache_clearpdf_cache_statspdf_get_tocpdf_infopdf_read_allpdf_read_pagespdf_render_pagespdf_searchserver_info

Topics

agentic-aiaiclaudecodex-clicopilotdocument-processingllmmcpmcp-servermodel-context-protocolopencodepdfpython

pdf-mcp

Quick Install

README Excerpt

Tools (9)

Topics

Related AI/LLM Servers