Back to Browse

Pymupdf MCP Server

Developer ToolsUse Caution4.2MCP RegistryLocal
Free

Server data from the Official MCP Registry

MCP server for reading PDFs using PyMuPDF. Supports local files and URLs.

About

MCP server for reading PDFs using PyMuPDF. Supports local files and URLs.

Security Report

4.2
Use Caution4.2High Risk

This MCP server for reading PDFs via PyMuPDF is well-structured with proper error handling and appropriate input validation. No authentication is required, but this is reasonable given the server operates on local files and user-provided URLs. The main security concerns are minor: lack of input validation on max_pages/max_bytes parameters, absence of URL validation before download, and potential for SSRF via arbitrary URL downloads. These are low-severity issues that do not significantly impact the overall security posture. Supply chain analysis found 7 known vulnerabilities in dependencies (0 critical, 3 high severity). Package verification found 1 issue.

7 files analyzed · 13 issues found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

File System Read

Reads files on your machine. Normal for tools that analyze or process local data.

File System Write

Writes or modifies files on your machine. Check that this is expected for the tool.

HTTP Network Access

Connects to external APIs or services over the internet.

How to Install

Add this to your MCP configuration file:

{
  "mcpServers": {
    "io-github-penny4nonsense-mcp-pymupdf": {
      "args": [
        "mcp-pymupdf"
      ],
      "command": "uvx"
    }
  }
}

Documentation

View on GitHub

From the project's GitHub README.

mcp-pymupdf

An MCP server for reading PDFs using PyMuPDF. Supports local files and URLs.

Installation

pip install mcp-pymupdf

Tools

read_pdf

Extract text from a PDF file or URL.

{
  "source": "/path/to/file.pdf",
  "max_pages": 50,
  "max_bytes": 200000
}

get_page

Extract text from a specific page range.

{
  "source": "https://example.com/paper.pdf",
  "start_page": 3,
  "end_page": 8
}

get_metadata

Retrieve PDF metadata without reading full text.

{
  "source": "/path/to/file.pdf"
}

Usage with Claude Desktop

Add to your Claude Desktop config:

{
  "mcpServers": {
    "pdf": {
      "command": "mcp-pymupdf"
    }
  }
}

Notes

  • Scanned or image-based PDFs cannot be read without OCR
  • Mathematical notation may render as plain text approximations
  • URLs are downloaded to a temp file and deleted after reading

License

MIT

Reviews

No reviews yet

Be the first to review this server!