Happy slice of mcp pizzaMCP.pizza
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

pdf-tools-mcp

MCP.Pizza Chef: danielkennedy1

pdf-tools-mcp is an MCP server offering a robust suite of PDF manipulation capabilities including rendering pages as images, merging pages, extracting metadata and text, creating snippets, and combining documents. It supports both local and remote PDF operations, enabling fetching PDFs from URLs and processing them locally. Built with Python 3.12+, it integrates seamlessly with the MCP framework to provide structured PDF data and manipulation endpoints for LLM-powered workflows.

Use This MCP server To

Render PDF pages as images for visual previews Merge multiple PDF pages into a single continuous page Extract detailed metadata from PDF documents Extract and analyze text blocks from PDFs Create custom snippets from PDF pages for focused content Combine pages from multiple PDFs into one document Download and process remote PDFs from URLs Enable LLMs to interact with and manipulate PDFs in real time

README

PDF Tools MCP

A comprehensive set of PDF manipulation tools built with the Model Context Protocol (MCP) framework.

Features

Local PDF Operations

  • Display: Render PDF pages as images
  • Merge: Combine multiple pages into a single long page
  • Metadata: Extract document metadata
  • Text: Extract text blocks and detailed text information
  • Snippets: Create freeform or full-width snippets from PDF pages
  • Fuse: Combine pages from multiple documents into a single document

Remote PDF Operations

  • Display: Render remote PDF pages as images
  • Download: Fetch PDFs from URLs to local storage

Installation

# Clone the repository
git clone https://github.com/yourusername/pdf-tools-mcp.git
cd pdf-tools-mcp

# Install dependencies
uv pip install -e .

Usage

Start the MCP server:

python -m src.main

The server provides PDF manipulation endpoints through the MCP protocol.

Development

  • Python 3.12+ required
  • Uses the MCP framework for tool registration
  • PDF documents are stored with UUID4 filenames for security
# Update dependencies
uv pip install -e . --upgrade

# Commit changes (uses conventional commit format)
cz commit

Dependencies

  • MCP Framework
  • PyMuPDF
  • aiohttp/aiofiles for async operations
  • python-magic-bin for file type detection

License

MIT. See LICENSE.

pdf-tools-mcp FAQ

How do I start the pdf-tools-mcp server?
Clone the repo, install dependencies with pip, then run 'python -m src.main' to start the server.
What Python version is required to run pdf-tools-mcp?
Python 3.12 or higher is required for compatibility.
Can pdf-tools-mcp handle PDFs from remote URLs?
Yes, it can download PDFs from URLs and process them locally.
What PDF operations does pdf-tools-mcp support?
It supports rendering pages as images, merging pages, extracting metadata and text, creating snippets, and fusing documents.
Is pdf-tools-mcp compatible with multiple LLM providers?
Yes, it works with MCP-compatible LLMs like OpenAI, Anthropic Claude, and Google Gemini.
How does pdf-tools-mcp expose its functionality?
It provides PDF manipulation endpoints through the MCP protocol for seamless integration.
Can I create custom snippets from PDFs using pdf-tools-mcp?
Yes, you can create freeform or full-width snippets from PDF pages.
Does pdf-tools-mcp support merging pages from different PDF documents?
Yes, it can fuse pages from multiple documents into a single PDF.