cellrank-MCP
About
A natural language interface for single-cell RNA sequencing (scRNA-Seq) analysis using the CellRank toolkit.
Details
- Author
- scmcphub
- GitHub stars
- 2
- Downloads
- 309
- Categories
- Developer Tools, Other
Jump to
- Natural‑language interface for scRNA-Seq analysis.
- IO module for reading and writing scRNA‑Seq data.
- Preprocessing functions: filtering, QC, normalization, scaling, HVG selection, PCA, neighbors.
- Tool module: clustering, differential expression analysis, and more.
- Plotting module: violin plots, heatmaps, dot plots.
Install via pip (pip install cellrank-mcp), then run locally with the command cellrank-mcp run. To use it in an MCP client, configure the server with the full path to the binary and the run argument. For remote usage, start the server with cellrank-mcp run --transport shttp --port 8000 and set the client’s URL to http://localhost:8000/mcp.
Natural language interface for scRNA-Seq analysis with cellrank through MCP.
- 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
- Anyone who wants to do scRNA-Seq analysis natural language!
- Agent developers who want to call cellrank's functions for their applications
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
scmcphub's complete documentation is available athttps://docs.scmcphub.org
A demo showing scRNA-Seq cell cluster analysis in a AI client Cherry Studio using natural language based on cellrank-mcp
Refer to the following configuration in your MCP client:
$ which cellrank /home/test/bin/cellrank-mcp
"mcpServers": { "cellrank-mcp": { "command": "/home/test/bin/cellrank-mcp", "args": [ "run" ] } }
Refer to the following configuration in your MCP client:
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" } }
If you have any questions, welcome to submit an issue, or contact me(hsh-me@outlook.com). Contributions to the code are also welcome!
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, 1196–1205 (2024).https://doi.org/10.1038/s41592-024-02303-9
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
Create crafted UI components inspired by the best 21st.dev design engineers.
Bring agent evaluations, observability, and synthetic test set generation directly into your IDE for free with Galileo's new MCP server
An MCP server to help AI assistants to answer questions and generate AccelByte Extend SDK code more effectively .
MCP server for AI Diagram Maker — generate beautiful software engineering diagrams directly inside Cursor, Claude Desktop, Claude Code, or any MCP-compatible AI agent
ALAPI MCP Tools,Call hundreds of API interfaces via MCP
AI-powered SVG animation generator that transforms static files into animated SVG components using the Allyson platform
MCP server that gives AI assistants on-demand access to 1,500+ amCharts docs, ~300 code examples, and 1000+ class API references.
APIMatic MCP Server is used to validate OpenAPI specifications using APIMatic. The server processes OpenAPI files and returns validation summaries by leveraging APIMatic’s API.
One shared context layer for AI agents and humans — live API specs, DB schemas, and versioned contracts across repos so every agent and teammate works from the same source of truth.
Build and deploy full-stack Next.js apps with 98 tools for React, AWS, and MongoDB
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
