markitdown-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@markitdown-mcpconvert this PDF to markdown and store it"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
markitdown-mcp
MCP server that converts documents to Markdown and stores them locally.
Tools
Tool | Description |
| Convert a file to Markdown. Supports PDF, DOCX, XLSX, PPTX, HTML, TXT, MD |
| Retrieve stored Markdown by |
| List processed documents |
| Keyword search across stored Markdown content |
| Metadata for a processed document |
Related MCP server: Local RAG
Requirements
Python 3.11+
Dependencies in
requirements.txt
Installation
bash setup.shStructure
markitdown-mcp/
├── mcp_server.py # MCP server (stdio)
├── src/
│ ├── converters.py # Conversion with markitdown
│ ├── database.py # SQLite (SQLAlchemy)
│ ├── models.py # ORM models
│ ├── schemas.py # Pydantic schemas
│ └── tools.py # Tool implementations
├── requirements.txt
└── setup.shCache
The server calculates an MD5 hash of each file. If the same file is processed twice, it returns the cached result without reprocessing.
Markdown files are stored in ~/.claude/skills/markitdown-mcp/data/cache/.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/alfredoanton82/markitdown-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server