Mcp Pymupdf

io.github.penny4nonsensePublished by GitHub account penny4nonsensev0.1.1Updated Oct 24, 2026

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

VerifiedSTDIODesktop onlyFiles & StorageKnowledge & Memory

Overview

AI-generated overview

Local MCP server that lets an assistant read PDFs from local paths or URLs with PyMuPDF, extracting text, page ranges and metadata.

What you can do
  • Extract text from a PDF given a local path or URL, with optional page and size limits
  • Read a specific page range from a PDF
  • Retrieve PDF metadata without reading the full text
When to use it
Useful when you want an assistant to pull text or metadata out of PDF documents, such as reports, papers or manuals, whether they sit on disk or behind a URL, without copying content by hand.
Requirements
Runs as a local process on the user's machine, installed from PyPI (pip install mcp-pymupdf); desktop-only, configured in the client's MCP config. No authentication, environment variables or headers are declared. Network access is needed to read PDFs from URLs.
Before you install
URLs are downloaded to a temporary file and deleted after reading, so remote content is fetched by the server. Text extraction is imperfect: scanned or image-based PDFs cannot be read without OCR, and mathematical notation may come out as plain-text approximations.

Installation

In SourceWeft

  1. Open Mcp Pymupdf in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

mcp-pymupdf

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

Installation

bash
pip install mcp-pymupdf

Tools

read_pdf

Extract text from a PDF file or URL.

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

get_page

Extract text from a specific page range.

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

get_metadata

Retrieve PDF metadata without reading full text.

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

Usage with Claude Desktop

Add to your Claude Desktop config:

json
{  "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

Source: README.md at commit b12ea7f

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts