PDF2MD

Extract PDF to markdown, to get around limitations such as context window or API limitations.

python

1

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": {
    "gavinhuang-pdf2md-mcp": {
      "command": "pdf2md-mcp",
      "args": []
    }
  }
}

You have a dedicated MCP server that uses AI-assisted processing to convert PDF files into Markdown. It supports local files and URLs, can resume where you left off, and writes output to a configurable directory for easy integration with your workflows.

How to use

Start the MCP server to expose the PDF to Markdown conversion capability. Then, from any MCP client that supports the protocol, call the convert_pdf_to_markdown tool with the path to your PDF and an optional output directory. You can point to local files or to a URL, and you can resume previous work if you previously began a conversion.

How to install

pip install pdf2md-mcp

pdf2md-mcp

Notes and capabilities

Output is Markdown generated from the PDF using AI-assisted content extraction.
You can convert from a local file path or a URL.
Conversion can be incremental; you can resume a previous task where you left off.
You can configure the output directory to organize generated Markdown files.

Available tools

convert_pdf_to_markdown

Converts a PDF file to Markdown format using AI sampling. Accepts a local file path or URL and outputs a Markdown file to an optional directory; returns the path to the generated Markdown, a summary of the task, and the number of pages processed.