Use This MCP server To

Perform scRNA-Seq data read/write using natural language commands Execute preprocessing steps like filtering and normalization via natural language Run clustering and differential expression analyses with simple prompts Generate visualizations such as violin plots and heatmaps from scRNA-Seq data Integrate Scanpy functions into AI agents and plugins for automated workflows Enable non-expert users to conduct scRNA-Seq analysis without coding Automate multi-step scRNA-Seq analysis pipelines in AI-enhanced environments

README

⚠️ Important Notice: This repository is no longer maintained. Please visit scmcphub for the latest version of MCP servers.

Scanpy MCP server

An MCP server for scRNA-Seq analysis software Scanpy with natural language!

🪩 What can it do?

IO module like read and write scRNA-Seq data with natural language
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

❓ Who is this for?

Anyone who wants to do scRNA-Seq analysis natural language!
Agent developers who want to call scanpy's functions for their applications

🌐 Where to use it?

You can use scanpy-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

🎬 Demo

A demo showing scRNA-Seq cell cluster analysis in a AI client Cherry Studio using natural language based on scanpy-mcp

Scanpy-mcp.demo.mp4

🏎️ Quickstart

Install

Install from PyPI

pip install scanpy-mcp

you can test it by running

scmcp run

run scnapy-server locally

Refer to the following configuration in your MCP client:

"mcpServers": {
  "scanpy-mcp": {
    "command": "scanpy-mcp",
    "args": [
      "run"
    ]
  }
}

run scnapy-server remotely

Refer to the following configuration in your MCP client:

run it in your server

scmcp run --transport shttp --port 8000

Then configure your MCP client, like this:

http://localhost:8000/mcp

🤝 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!

scanpy-mcp FAQ

How do I install the scanpy-mcp server?

Clone the repository from GitHub and follow the setup instructions; note the project is no longer maintained, so consider using scmcphub for the latest versions.

Can scanpy-mcp handle all Scanpy functions?

It covers core Scanpy modules like IO, preprocessing, clustering, differential expression, and plotting, but may not support every advanced feature.

Which AI clients support scanpy-mcp?

It works with MCP-compatible AI clients such as Cherry Studio, plugins like Cline, and agent frameworks like Agno.

Is programming knowledge required to use scanpy-mcp?

No, it allows natural language commands to perform complex scRNA-Seq analyses, making it accessible to non-programmers.

How does scanpy-mcp improve scRNA-Seq workflows?

By enabling natural language interaction, it simplifies data processing, analysis, and visualization without manual coding.

Is scanpy-mcp compatible with multiple LLM providers?

Yes, it is designed to work with various LLMs including OpenAI, Anthropic Claude, and Google Gemini.

Where can I find updated MCP servers for Scanpy?

Visit the scmcphub GitHub organization for the latest maintained MCP servers related to Scanpy.