What is Decoupler Mcp

decoupler-mcp is an MCP server designed for analyzing biological activities, specifically for single-cell RNA sequencing (scRNA-Seq) using a natural language interface.

Use cases

Use cases include performing scRNA-Seq analysis using natural language queries, enabling agent developers to integrate decoupler’s functionalities into their applications.

How to use

To use decoupler-mcp, install it via PyPI with ‘pip install decoupler-mcp’. You can run it locally or remotely by configuring your MCP client accordingly.

Key features

Key features include an IO module for reading and writing scRNA-Seq data, pathway activity and transcription factor inference, clustering and differential expression tools, and various plotting options like violin plots and UMAP/t-SNE visualizations.

Where to use

decoupler-mcp can be used in various AI clients, plugins, or agent frameworks that support MCP, such as Cherry Studio, Cline, and Agno.

decoupler-MCP

Natural language interface for scRNA-Seq analysis with decoupler through MCP.

🪩 What can it do?

• IO module like read and write scRNA-Seq data
• Pathway activity/Transcription factor inference
• Tool module, like clustering, differential expression etc.
• Plotting module, like violin, umap/tsne

❓ Who is this for?

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

🌐 Where to use it?

You can use decoupler-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 decoupler-mcp

📚 Documentation

scmcphub’s complete documentation is available at https://docs.scmcphub.org

🏎️ Quickstart

Install

Install from PyPI

pip install decoupler-mcp

you can test it by running

decoupler-mcp run

run decoupler-mcp locally

Refer to the following configuration in your MCP client:

check path

$ which decoupler 
/home/test/bin/decoupler-mcp

"mcpServers": {
  "decoupler-mcp": {
    "command": "/home/test/bin/decoupler-mcp",
    "args": [
      "run"
    ]
  }
}

run decoupler-server remotely

Refer to the following configuration in your MCP client:

run it in your server

decoupler-mcp run --transport shttp --port 8000

Then configure your MCP client in local AI client, like this:

"mcpServers": {
  "decoupler-mcp": {
    "url": "http://localhost:8000/mcp"
  }
}

🤝 Contributing

If you have any questions, welcome to submit an issue, or contact me([email protected]). Contributions to the code are also welcome!

Citing

If you use decoupler-mcp in for your research, please consider citing following work:

Badia-i-Mompel P., Vélez Santiago J., Braunger J., Geiss C., Dimitrov D., Müller-Dott S., Taus P., Dugourd A., Holland C.H., Ramirez Flores R.O. and Saez-Rodriguez J. 2022. decoupleR: ensemble of computational methods to infer biological activities from omics data. Bioinformatics Advances. https://doi.org/10.1093/bioadv/vbac016