Scmcp

🚀 SCMCP

A multi-language computing platform (MCP) server for single-cell RNA sequencing (scRNA-Seq) analysis, supporting natural language processing!

🚀 Quick Start

Installation

Install via PyPI:

pip install scmcp

You can test it by running the following command:

scmcp run

Run scnapy-server locally

Refer to the following configuration in your MCP client:

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

Run scnapy-server remotely

Run with the following configuration on the server:

scmcp run --transport sse --port 8000

Then configure it in your MCP client as follows:

http://localhost:8000/sse

✨ 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 selection, principal component analysis (PCA), and neighbor calculation.
• Tool Module: Such as clustering analysis and differential expression analysis.
• Plotting Module: Generate visualizations like violin plots, heatmaps, and dot plots.
• Cell-Cell Communication Analysis: Study cell-cell interactions.

🎯 Target Users

• All researchers who wish to perform scRNA-Seq analysis using natural language.
• Developers who want to call scanpy functions for their application services.

🌐 Usage Scenarios

You can use SCMCP 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 demonstration video of using natural language for scRNA-Seq cell clustering analysis in the AI client Cherry Studio:

https://github.com/user-attachments/assets/93a8fcd8-aa38-4875-a147-a5eeff22a559

🤝 Contribution and Contact

If you have any questions, feel free to submit an issue or contact us at hsh-me@outlook.com. We also welcome you to contribute to the code!