MCP PDF Reader

Local MCP server to read PDF files

python

3

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": {
    "mlexpertio-mcp-pdf-reader": {
      "command": "python",
      "args": [
        "server.py"
      ]
    }
  }
}

You can run an MCP server that exposes PDF reading capabilities. This server converts PDF content into clean Markdown and lets you discover and access available PDFs securely through a simple MCP client workflow.

How to use

You interact with the server through an MCP client to list available PDFs and extract their full text in Markdown format. Use the two built‑in tools to access content efficiently:

get_document_list: Retrieve a list of all PDF files located in the data directory. Use this to discover what documents you can process.
get_document_text: Request the full text of a specific PDF file and receive it in Markdown. This lets you work with the content in a readable, portable format.

How to install

Prerequisites you need before starting include Python and a runtime for MCP servers. You will also run the server using a standard MCP transport.

Clone the project and enter the directory where the server code resides.

Install Python and set up the environment, following these steps.

iris-like steps from the source you will execute are as follows:

uv python install 3.12.10

Additional notes

Place your PDF documents in the data/ directory. The server detects them automatically and makes them available through the two tools.

Run the MCP server using the standard command: python server.py. The server uses stdio transport and can be integrated with any MCP‑compatible client.

For development and testing, you can use the MCP inspector to interact with the server and inspect tool responses via a web interface.

If you want to integrate this MCP server with an editor, you can configure a new MCP server within your editor’s MCP tooling, pointing to the same local start command.

Usage workflow for developers

Add PDFs to the data/ directory. The server will automatically expose them through get_document_list and get_document_text.
Start the server with python server.py. Ensure the environment has the required runtime and dependencies.
Use an MCP client or the MCP inspector to call get_document_list to find available PDFs, then call get_document_text with a file name to retrieve the Markdown content.

Development and editor integration

You can test and debug using the MCP inspector, which opens a web interface to run tools and view responses.

In editors that support MCP, add a new MCP Server configuration and point it to the local server start command so you can directly run and test tool calls from your editor.

Available tools

get_document_list

Returns a list of all available PDF files in the data directory so you can discover which documents you can process.

get_document_text

Extracts and returns the full text content of a specified PDF file in Markdown format, enabling easy reading and processing.