markitdown-mcp
Python tool for converting files and office documents to Markdown.
- • Core MCP protocol features implemented (24/40)
- • Strong GitHub community (20/20)
- • Optimal dependency management (20/20)
- • Full deployment maturity (10/10)
- • Documentation (8/8)
- • Archestra MCP Trust score badge is missing
{
"markitdown-mcp-stdio": {
"command": "markitdown-mcp",
"args": [],
"env": {}
},
"markitdown-mcp-http": {
"command": "markitdown-mcp",
"args": [
"--http",
"--host",
"127.0.0.1",
"--port",
"3001"
],
"env": {}
},
"markitdown-mcp-docker-basic": {
"command": "docker",
"args": [
"run",
"-it",
"--rm",
"markitdown-mcp:latest"
],
"env": {},
"docker_image": "markitdown-mcp:latest"
},
"markitdown-mcp-docker-mounted": {
"command": "docker",
"args": [
"run",
"-it",
"--rm",
"-v",
"/home/user/data:/workdir",
"markitdown-mcp:latest"
],
"env": {},
"docker_image": "markitdown-mcp:latest"
},
"markitdown-mcp-docker-claude-desktop": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"markitdown-mcp:latest"
],
"env": {},
"docker_image": "markitdown-mcp:latest"
},
"markitdown-mcp-docker-claude-desktop-mounted": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-v",
"/home/user/data:/workdir",
"markitdown-mcp:latest"
],
"env": {},
"docker_image": "markitdown-mcp:latest"
}
}MarkItDown-MCP
The markitdown-mcp package provides a lightweight STDIO, Streamable HTTP, and SSE MCP server for calling MarkItDown.
It exposes one tool: convert_to_markdown(uri), where uri can be any http:, https:, file:, or data: URI.
Installation
To install the package, use pip:
pip install markitdown-mcp
Usage
To run the MCP server, using STDIO (default) use the following command:
markitdown-mcp
To run the MCP server, using Streamable HTTP and SSE use the following command:
markitdown-mcp --http --host 127.0.0.1 --port 3001
Running in Docker
To run markitdown-mcp in Docker, build the Docker image using the provided Dockerfile:
docker build -t markitdown-mcp:latest .
And run it using:
docker run -it --rm markitdown-mcp:latest
This will be sufficient for remote URIs. To access local files, you need to mount the local directory into the container. For example, if you want to access files in /home/user/data, you can run:
docker run -it --rm -v /home/user/data:/workdir markitdown-mcp:latest
Once mounted, all files under data will be accessible under /workdir in the container. For example, if you have a file example.txt in /home/user/data, it will be accessible in the container at /workdir/example.txt.
Accessing from Claude Desktop
It is recommended to use the Docker image when running the MCP server for Claude Desktop.
Follow these instructions to access Claude's claude_desktop_config.json file.
Edit it to include the following JSON entry:
{
"mcpServers": {
"markitdown": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"markitdown-mcp:latest"
]
}
}
}
If you want to mount a directory, adjust it accordingly:
{
"mcpServers": {
"markitdown": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-v",
"/home/user/data:/workdir",
"markitdown-mcp:latest"
]
}
}
}
Debugging
To debug the MCP server you can use the mcpinspector tool.
npx @modelcontextprotocol/inspector
You can then connect to the inspector through the specified host and port (e.g., http://localhost:5173/).
If using STDIO:
- select
STDIOas the transport type, - input
markitdown-mcpas the command, and - click
Connect
If using Streamable HTTP:
- select
Streamable HTTPas the transport type, - input
http://127.0.0.1:3001/mcpas the URL, and - click
Connect
If using SSE:
- select
SSEas the transport type, - input
http://127.0.0.1:3001/sseas the URL, and - click
Connect
Finally:
- click the
Toolstab, - click
List Tools, - click
convert_to_markdown, and - run the tool on any valid URI.
Security Considerations
The server does not support authentication, and runs with the privileges of the user running it. For this reason, when running in SSE or Streamable HTTP mode, it is recommended to run the server bound to localhost (default).
Trademarks
This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft
trademarks or logos is subject to and must follow
Microsoft's Trademark & Brand Guidelines.
Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship.
Any use of third-party trademarks or logos are subject to those third-party's policies.
[](https://archestra.ai/mcp-catalog/microsoft__markitdown__packages__markitdown-mcp)MarkItDown-MCP
The markitdown-mcp package provides a lightweight STDIO, Streamable HTTP, and SSE MCP server for calling MarkItDown.
It exposes one tool: convert_to_markdown(uri), where uri can be any http:, https:, file:, or data: URI.
Installation
To install the package, use pip:
pip install markitdown-mcp
Usage
To run the MCP server, using STDIO (default) use the following command:
markitdown-mcp
To run the MCP server, using Streamable HTTP and SSE use the following command:
markitdown-mcp --http --host 127.0.0.1 --port 3001
Running in Docker
To run markitdown-mcp in Docker, build the Docker image using the provided Dockerfile:
docker build -t markitdown-mcp:latest .
And run it using:
docker run -it --rm markitdown-mcp:latest
This will be sufficient for remote URIs. To access local files, you need to mount the local directory into the container. For example, if you want to access files in /home/user/data, you can run:
docker run -it --rm -v /home/user/data:/workdir markitdown-mcp:latest
Once mounted, all files under data will be accessible under /workdir in the container. For example, if you have a file example.txt in /home/user/data, it will be accessible in the container at /workdir/example.txt.
Accessing from Claude Desktop
It is recommended to use the Docker image when running the MCP server for Claude Desktop.
Follow these instructions to access Claude's claude_desktop_config.json file.
Edit it to include the following JSON entry:
{
"mcpServers": {
"markitdown": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"markitdown-mcp:latest"
]
}
}
}
If you want to mount a directory, adjust it accordingly:
{
"mcpServers": {
"markitdown": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-v",
"/home/user/data:/workdir",
"markitdown-mcp:latest"
]
}
}
}
Debugging
To debug the MCP server you can use the mcpinspector tool.
npx @modelcontextprotocol/inspector
You can then connect to the inspector through the specified host and port (e.g., http://localhost:5173/).
If using STDIO:
- select
STDIOas the transport type, - input
markitdown-mcpas the command, and - click
Connect
If using Streamable HTTP:
- select
Streamable HTTPas the transport type, - input
http://127.0.0.1:3001/mcpas the URL, and - click
Connect
If using SSE:
- select
SSEas the transport type, - input
http://127.0.0.1:3001/sseas the URL, and - click
Connect
Finally:
- click the
Toolstab, - click
List Tools, - click
convert_to_markdown, and - run the tool on any valid URI.
Security Considerations
The server does not support authentication, and runs with the privileges of the user running it. For this reason, when running in SSE or Streamable HTTP mode, it is recommended to run the server bound to localhost (default).
Trademarks
This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft
trademarks or logos is subject to and must follow
Microsoft's Trademark & Brand Guidelines.
Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship.
Any use of third-party trademarks or logos are subject to those third-party's policies.
Related MCP Servers
mcp-shrimp-task-manager
88/100Shrimp Task Manager is a task tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like developer behavior in reasoning AI systems.
cognee-mcp
86/100Memory for AI Agents in 5 lines of code
shadcn-ui-mcp-server
82/100A mcp server to allow LLMS gain context about shadcn ui component structure,usage and installation,compaitable with react,svelte 5,and vue
mobile-mcp
81/100Model Context Protocol Server for Mobile Automation and Scraping (iOS, Android, Emulators, Simulators and Real Devices)
HuggingFace
80/100Remote MCP server for HuggingFace services - access models, datasets, and spaces
magic-mcp
79/100It's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic
