Scanpy MCP

🚀 Scanpy MCP Server

An MCP server for the single-cell RNA sequencing (scRNA-Seq) analysis software Scanpy, supporting natural language processing!

✨ Features

• Input and Output Module: Read and write scRNA-Seq data using natural language.
• Preprocessing Module: Includes functions such as filtering, quality control, normalization, scaling, highly variable gene detection, PCA, and neighbor analysis.
• Tool Module: Such as clustering and differential expression analysis.
• Plotting Module: Generate violin plots, heatmaps, dot plots, etc.

👥 Target Users

• All users who wish to perform scRNA-Seq analysis using natural language.
• Developers who want to call Scanpy functions in their applications.

🌐 Use Cases

You can use scanpy-mcp in most AI clients, plugins, or proxy frameworks that support MCP:

• AI clients, such as Cherry Studio.
• Plugins, such as Cline.
• Proxy frameworks, such as Agno.

🎬 Demo

A demo video showing the use of natural language for scRNA-Seq cell clustering analysis in the AI client Cherry Studio. Link

🚀 Quick Start

Installation

Install from PyPI:

pip install scanpy-mcp

You can test it by running the following command:

scmcp run

Run scanpy-server Locally

Refer to the following configuration in your MCP client:

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

Run scanpy-server Remotely

Run on the server:

scmcp run --transport sse --port 8000

Then configure your MCP client, for example:

http://localhost:8000/sse

🤝 Contribution and Contact

If you have any questions, please submit an issue or contact me via the following email (hsh-me@outlook.com). Contributions to the code are also welcome!