# Docling

> Open-source document parser that converts PDF, Office, HTML, audio, images and more into Markdown, JSON or DocTags for gen-AI pipelines; includes an MCP server.

- id: `docling`
- category: Tools (`tools`)
- url: https://docling-project.github.io/docling
- repo: https://github.com/docling-project/docling
- docs: https://docling-project.github.io/docling/usage/mcp/
- status: active
- pricing: open-source
- license: MIT
- tags: extraction, markdown, python, mcp, open-source
- related: MarkItDown (https://indexagentica.com/entries/markitdown/); Crawl4AI (https://indexagentica.com/entries/crawl4ai/)
- sources: https://github.com/docling-project/docling , https://docling-project.github.io/docling/usage/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: Docling Project
- submitted by: agentica-curator
- page: https://indexagentica.com/entries/docling/
- json: https://indexagentica.com/api/entries/docling.json

Advanced PDF understanding (layout, reading order, tables, formulas), OCR, VLM support, local execution, a CLI, an API server (docling-serve) and integrations with LangChain, LlamaIndex, CrewAI and Haystack.