https://github.com/scmcphub/cellrank-mcp
MCP server for trajectory inference using cellrank
https://github.com/scmcphub/cellrank-mcp
Last synced: about 2 months ago
JSON representation
MCP server for trajectory inference using cellrank
- Host: GitHub
- URL: https://github.com/scmcphub/cellrank-mcp
- Owner: scmcphub
- Created: 2025-04-17T11:01:36.000Z (7 months ago)
- Default Branch: main
- Last Pushed: 2025-06-27T12:03:03.000Z (4 months ago)
- Last Synced: 2025-06-27T12:15:26.905Z (4 months ago)
- Language: Python
- Size: 48.8 KB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-mcp-servers - **cellrank-mcp** - MCP server for trajectory inference using cellrank `python` `mcp` `server` `pip install git+https://github.com/scmcphub/cellrank-mcp` (AI/ML)
- awesome-mcp-servers - **cellrank-mcp** - MCP server for trajectory inference using cellrank `python` `mcp` `server` `pip install git+https://github.com/scmcphub/cellrank-mcp` (đ¤ AI/ML)
README
# cellrank-MCP
Natural language interface for scRNA-Seq analysis with cellrank through MCP.
## đĒŠ What can it do?
- IO module like read and write scRNA-Seq data
- Preprocessing module,like filtering, quality control, normalization, scaling, highly-variable genes, PCA, Neighbors,...
- Tool module, like clustering, differential expression etc.
- Plotting module, like violin, heatmap, dotplot
## â Who is this for?
- Anyone who wants to do scRNA-Seq analysis natural language!
- Agent developers who want to call cellrank's functions for their applications
## đ Where to use it?
You can use cellrank-mcp in most AI clients, plugins, or agent frameworks that support the MCP:
- AI clients, like Cherry Studio
- Plugins, like Cline
- Agent frameworks, like Agno
## đ Documentation
scmcphub's complete documentation is available at https://docs.scmcphub.org
## đŦ Demo
A demo showing scRNA-Seq cell cluster analysis in a AI client Cherry Studio using natural language based on cellrank-mcp
## đī¸ Quickstart
### Install
Install from PyPI
```
pip install cellrank-mcp
```
you can test it by running
```
cellrank-mcp run
```
#### run cellrank-mcp locally
Refer to the following configuration in your MCP client:
check path
```
$ which cellrank
/home/test/bin/cellrank-mcp
```
```
"mcpServers": {
"cellrank-mcp": {
"command": "/home/test/bin/cellrank-mcp",
"args": [
"run"
]
}
}
```
#### run cellrank-server remotely
Refer to the following configuration in your MCP client:
run it in your server
```
cellrank-mcp run --transport shttp --port 8000
```
Then configure your MCP client in local AI client, like this:
```
"mcpServers": {
"cellrank-mcp": {
"url": "http://localhost:8000/mcp"
}
}
```
## đ¤ Contributing
If you have any questions, welcome to submit an issue, or contact me(hsh-me@outlook.com). Contributions to the code are also welcome!
## Citing
If you use cellRank-mcp in for your research, please consider citing following work:
> Weiler, P., Lange, M., Klein, M. et al. CellRank 2: unified fate mapping in multiview single-cell data. Nat Methods 21, 1196â1205 (2024). https://doi.org/10.1038/s41592-024-02303-9