how-to-guide

How to Handle Proprietary File Formats with MarkItDown Custom Plugins

April 11, 2026 microsoft/markitdown ↗

Create a Python package implementing the DocumentConverter interface, register the converter via the register_converters hook, and expose the markitdown.plugin entry point in pyproject.toml to enable automatic discovery when using the --use-plugins flag.

The microsoft/markitdown library provides robust conversion for common formats, but enterprise workflows often require processing proprietary or domain-specific file types. By building custom plugins that adhere to the DocumentConverter abstraction defined in src/markitdown/_base_converter.py, you can extend the tool to handle any binary or text format while leveraging

Have a question about this repo?

These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:

Share the following with your agent to get started:

curl -s "https://instagit.com/install.md"

Add to your MCP client configuration:

{
  "mcpServers": {
    "instagit": {
      "command": "npx",
      "args": ["-y", "instagit@latest"]
    }
  }
}

Ask your agent:

"Use Instagit MCP to understand how microsoft/markitdown works."

Works with

Claude Codex Cursor VS Code OpenClaw Any MCP Client

Maintain an open-source project? Get it listed too →