cellrank-MCP

What is cellrank-MCP?

cellrank-MCP is a natural language interface for scRNA-Seq analysis that exposes cellrank functions through the Model Context Protocol. It is designed for researchers and agent developers who want to perform single-cell RNA sequencing workflows using conversational AI clients or agentic frameworks.

How to use cellrank-MCP?

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.

Key features of cellrank-MCP

• 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.

Use cases of cellrank-MCP

• Perform complete scRNA‑Seq analysis pipelines using only natural language in an AI client.
• Integrate cellrank capabilities into agentic frameworks (e.g., Agno) for automated data processing.
• Add single‑cell analysis features to plugins like Cline.
• Use Cherry Studio to interactively explore cell cluster results.

FAQ from cellrank-MCP

What analysis modules are available?

cellrank-MCP covers IO, preprocessing (filtering, QC, normalization, scaling, HVG, PCA, neighbors), tools (clustering, differential expression), and plotting (violin, heatmap, dotplot).

Who should use cellrank-MCP?

Anyone who wants to perform scRNA-Seq analysis through natural language, as well as agent developers who need to call cellrank functions programmatically.

How do I install and run cellrank-MCP?

Install it from PyPI with pip install cellrank-mcp. Verify the installation with cellrank-mcp run, then configure your MCP client with the command and the run argument.

Can I run cellrank-MCP on a remote server?

Yes. Start the server with cellrank-mcp run --transport shttp --port 8000 and set your client’s URL to http://localhost:8000/mcp.

What types of MCP clients are supported?

cellrank-MCP works with any MCP‑compatible client, including Cherry Studio (AI client), Cline (plugin), and Agno (agent framework).