Pymupdf4llm MCP Server

PyMuPDF Utilities for LLM/RAG

Local serverstdioPython

What is the Pymupdf4llm MCP server?

PyMuPDF Utilities for LLM/RAG. That is what the pymupdf4llm mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

PyMuPDF4LLM is a lightweight extension for PyMuPDF that converts documents into structured Markdown, JSON, and plain text optimised for RAG pipelines, vector embeddings, and LLM ingestion. It handles multi-column layouts, tables, images, headers, and scanned pages with automatic OCR — all powered by the MuPDF C engine.

  • One import, three output formats — — Markdown, JSON, and plain text out of the box
  • No GPU, no cloud — — runs on any machine that can run Python
  • Layout-aware — — multi-column pages, reading-order reconstruction, table detection
  • Smart OCR — — automatically OCRs only the regions that need it, skipping clean text
  • Framework integrations — — drop-in support for LlamaIndex and LangChain
  • Page chunking — — chunk output by page with full metadata per chunk, ready for vector stores

The tools it exposes

The server publishes 1 tool. What each one is for:

  • Configuration — The default behaviour requires no configuration — just install Tesseract and it works:

Getting it running

The server ships on PyPI as pymupdf4llm, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

How it compares

Among the AI and media services options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Pymupdf4llm's toolset — Configuration — is a fair guide to whether it matches your workflow. It is maintained by Artifex; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Pymupdf4llm's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
ConfigurationThe default behaviour requires no configuration — just install Tesseract and it works:

How to install the Pymupdf4llm MCP server

{
  "mcpServers": {
    "pymupdf4llm": {
      "command": "uvx",
      "args": ["pymupdf4llm"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Pymupdf4llm to Configuration.

Frequently asked questions

It connects Pymupdf4llm to MCP-compatible AI assistants such as Claude and Cursor, exposing 1 tool (Configuration) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Pymupdf4llm directly.