luciano/markitdown
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Add running with uv instructions

Browse source
This commit is contained in:
Cedric Vidal 2025-04-25 09:26:37 -07:00
parent 041be54471
commit 65166375fd
1 changed files with 23 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

23
packages/markitdown-mcp/README.md
View file

@ -50,6 +50,14 @@ 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`. 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`.
## Running using uv
[uv](https://docs.astral.sh/uv/) is an extremely fast alternative to [pip](https://pip.pypa.io/en/stable/) which allows running Python packages without installing them.
```
uvx markitdown-mcp
```
## Accessing from Claude Desktop ## Accessing from Claude Desktop
It is recommended to use the Docker image when running the MCP server for Claude Desktop. It is recommended to use the Docker image when running the MCP server for Claude Desktop.
@ -94,6 +102,21 @@ If you want to mount a directory, adjust it accordingly:
} }
``` ```
Alternatively, using `uv`:
```json
{
"mcpServers": {
"markitdown": {
"command": "uvx",
"args": [
"markitdown-mcp"
]
}
}
}
```
## Debugging ## Debugging
To debug the MCP server you can use the `mcpinspector` tool. To debug the MCP server you can use the `mcpinspector` tool.