Documents

MCP tool for LLM interaction with EPUB and PDF files.
  • python

8

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "jbchouinard-mcp-document-reader": {
      "command": "poetry",
      "args": [
        "-C",
        "path/to/mcp-document-reader",
        "run",
        "mcp-document-reader"
      ]
    }
  }
}

You have a lightweight MCP server that enables you to interact with PDF and EPUB documents. It runs locally via Python tooling and can be consumed by any MCP client to load documents, perform actions, and fetch results in a structured way.

How to use

Connect your MCP client to the server to access document processing features. You can run the server locally using your package manager and then point your client to the appropriate runtime. The server supports multiple startup methods, including a Poetry-based local runtime and a direct script execution. When running locally, you’ll launch the server and then use the MCP client to request document loading, parsing, indexing, and query operations as needed.

How to install

Prerequisites: Python 3.11 or newer, Poetry.

# Clone the repository
git clone https://github.com/jbchouinard/mcp-document-reader.git
cd mcp-document-reader
poetry install

Configuration and startup methods

Two explicit startup configurations are supported. Use the one that matches how you want to run the server on your machine.

{
  "mcpServers": {
    "documents": {
      "command": "poetry",
      "args": ["-C", "path/to/mcp-document-reader", "run", "mcp-document-reader"]
    }
  }
}
{
  "mcpServers": {
    "documents": {
      "command": "/path/to/mcp-document-reader",
      "args": []
    }
  }
}

Notes

If you prefer running the server directly after building, you can build the project and install the wheel, then run the script as shown, and reference the installed path in your configuration.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational
Documents MCP Server - jbchouinard/mcp-document-reader | VeilStrat