PyMuPDF4LLM MCP Server

MCPOpen SourceBSD-3-Clause20.5

by ai-zerolab • NLP & LLM

An MCP server that converts PDFs to Markdown (optimized for LLM workflows) and exposes that functionality via stdio or SSE.

Example Use Cases

1
Extract and convert PDF documents into clean Markdown suitable for LLM consumption.
2
A lightweight MCP endpoint (stdio or SSE) to provide PDF-to-Markdown conversion to MCP-capable clients like cursor or windsurf.
3
Integrate PyMuPDF-based processing (text, structure, and assets) into downstream LLM pipelines for summarization, Q&A, or indexing.

Description

This project provides an MCP server for the pymupdf4llm tooling, enabling export of PDF content to Markdown for downstream LLM consumption. It can be run in stdio or SSE modes and integrates with MCP clients (e.g., cursor, windsurf) via a simple uvx command. The README points to documentation and an official upstream repo, and the server is intended to simplify PDF-to-Markdown conversion and integration into agent workflows.

Quick Actions

View on GitHub

Security

Scanned 2 month(s) ago

Risk Level

MINIMAL

Read-only data retrieval, no side effects

Trust Score

D44/100

4/17 checks passed

Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.

Quick Stats

Service TypeMCP

Pricing ModelFree

Capabilities0 Tools / 0 Prompts / 0 Resources

Ownerai-zerolab

CategoryNLP & LLM

DependenciesStandalone