mcpField
P
PDF Tools MCP

PDF Tools MCP

Local
github.com/danielkennedy1Files & Storage32Updated 76w ago

About PDF Tools MCP

PDF Tools MCP is a set of PDF manipulation tools built on the MCP framework, covering local and remote documents. It suits users who need to render, merge, extract or download PDFs. The project is written in Python and uses PyMuPDF.

Key features

  1. 01Render PDF pages as images
  2. 02Merge multiple pages into one long page
  3. 03Extract metadata and text information
  4. 04Combine pages from several documents
  5. 05Download remote PDFs to local storage

Use cases

  1. 01Previewing PDF pages from an MCP client
  2. 02Extracting text and metadata from PDFs
  3. 03Combining pages from several documents into one file

MCP support

This is an MCP server that registers PDF processing tools for MCP clients to call through the protocol.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"pdf-tools": {
"command": "npx",
"args": [
"-y",
"@smithery/cli"
]
}
}
}
Run commandnpx -y @smithery/cli

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@smithery/cli

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

PDF Tools MCP

smithery badge

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

Installing via Smithery

To install PDF Tools for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @danielkennedy1/pdf-tools-mcp --client claude
Manual 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.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.