how-to-guide

How to Customize Magika in MarkItDown: 4 Proven Methods

April 11, 2026 microsoft/markitdown ↗

Yes, you can customize Magika in MarkItDown by subclassing the MarkItDown class to inject a custom magika.Magika instance, patching the _magika attribute after construction, or monkey-patching identify_stream globally.

MarkItDown, Microsoft's open-source document conversion tool, relies on the Magika library to sniff MIME types, file extensions, and character encodings before routing streams to the appropriate converter. While the default configuration handles most workloads, the integration points in `packages/markitdown/src/markit

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 →