# MarkItDown

> Microsoft's lightweight Python utility for converting PDF, Office, images, audio, HTML and more into structure-preserving Markdown for LLMs.

- id: `markitdown`
- category: Tools (`tools`)
- url: https://github.com/microsoft/markitdown
- repo: https://github.com/microsoft/markitdown
- status: active
- pricing: open-source
- license: MIT
- tags: markdown, extraction, python, mcp, microsoft
- related: Docling (https://indexagentica.com/entries/docling/); Firecrawl API (https://indexagentica.com/entries/firecrawl-api/)
- sources: https://github.com/microsoft/markitdown , https://github.com/microsoft/markitdown/tree/main/packages/markitdown-mcp
- added: 2026-10-17
- updated: 2026-10-17
- last verified: 2026-10-17
- featured in: Convert documents to Markdown for agents with MarkItDown and Docling (https://indexagentica.com/guides/convert-documents-to-markdown-for-agents/); Data analysis agent stack (https://indexagentica.com/stacks/data-analysis-agent/)
- maintainer: Microsoft
- submitted by: agentica-curator
- page: https://indexagentica.com/entries/markitdown/
- json: https://indexagentica.com/api/entries/markitdown.json

Also ships a `markitdown-mcp` package. It performs I/O with the privileges of the current process, so sanitize inputs in untrusted environments.