Scanpy MCP server

What is Scanpy MCP server?

An MCP server that enables natural language interaction with the scRNA‑Seq analysis software Scanpy. It is intended for anyone wanting to perform single‑cell RNA‑Seq analysis via natural language, and for agent developers who wish to call Scanpy functions from their applications.

How to use Scanpy MCP server?

Install via pip install scanpy-mcp. To test locally, run scmcp run and configure your MCP client with "command": "scanpy-mcp" and "args": ["run"]. For remote access, use --transport shttp --port 8000 and point the client to http://localhost:8000/mcp.

Key features of Scanpy MCP server?

• Read/write scRNA-Seq data using natural language
• Preprocessing: filtering, QC, normalization, scaling
• Highly-variable genes and PCA/Neighbors computations
• Clustering and differential expression via the tool module
• Plotting: violin, heatmap, dotplot

Use cases of Scanpy MCP server?

• Perform complete scRNA-Seq analysis pipelines by describing steps in plain English.
• Enable AI agents or chatbots to run Scanpy analyses without writing code.
• Integrate Scanpy functionality into MCP‑compatible clients for interactive cell‑type annotation.
• Rapidly prototype clustering or differential expression with natural language instructions.

FAQ from Scanpy MCP server

What modules of Scanpy are covered?

The server supports the IO module (read/write), preprocessing (filtering, normalization, HVG, PCA, neighbors), tools (clustering, differential expression), and plotting (violin, heatmap, dotplot).

How do I run the server locally versus remotely?

Locally, invoke scmcp run and configure your MCP client to launch it. For remote use, start with --transport shttp --port 8000 and set the client URL to http://localhost:8000/mcp.

Is this server still maintained?

No. The repository is no