Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT and other tools is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AI Fire in da houseCheck it out free

pymupdf4llm-mcp

MCP.Pizza Chef: pymupdf

pymupdf4llm-mcp is an MCP server designed to convert PDF documents into markdown format optimized for large language models. It enables seamless extraction and structuring of PDF content, facilitating real-time interaction and processing by LLMs. This server supports multiple communication modes like stdio and SSE, making it adaptable for various MCP clients and workflows.

Use This MCP server To

Convert PDF documents to markdown for LLM processing Extract structured text from PDFs for AI workflows Integrate PDF content into LLM-powered applications Enable real-time PDF content streaming via SSE Support multi-mode communication with MCP clients Automate PDF data extraction for knowledge bases Facilitate markdown export for document summarization

README

pymupdf4llm-mcp

Release Build status Commit activity License

MCP Server for pymupdf4llm, best for export PDF to markdown for LLM.

Quick Start

Run the following command to run the MCP server:

uvx pymupdf4llm-mcp@latest stdio # stdio mode
# or
uvx pymupdf4llm-mcp@latest sse # sse mode

Configure your cursor/windsurf/... and other MCP client to this server:

{
  "mcpServers": {
    "pymupdf4llm-mcp": {
      "command": "uvx",
      "args": [
        "pymupdf4llm-mcp@latest",
        "stdio"
      ],
      "env": {}
    }
  }
}

pymupdf4llm-mcp FAQ

How do I start the pymupdf4llm-mcp server?
Run 'uvx pymupdf4llm-mcp@latest stdio' for stdio mode or 'uvx pymupdf4llm-mcp@latest sse' for SSE mode.
What communication modes does pymupdf4llm-mcp support?
It supports stdio and server-sent events (SSE) modes for flexible client integration.
Can pymupdf4llm-mcp handle large PDF files efficiently?
Yes, it is optimized for efficient PDF to markdown conversion suitable for large documents.
How do I connect an MCP client to pymupdf4llm-mcp?
Configure your MCP client (e.g., cursor or windsurf) to communicate with the server using the specified stdio or SSE mode.
Is pymupdf4llm-mcp compatible with multiple LLM providers?
Yes, it works with models from OpenAI, Anthropic Claude, and Google Gemini by providing markdown output for LLM consumption.
What formats does pymupdf4llm-mcp output?
It outputs markdown-formatted text extracted from PDFs, optimized for LLM input.
Is pymupdf4llm-mcp open source?
Yes, it is open source and available on GitHub under a permissive license.