mcpField
S
Scanpy MCP server

Scanpy MCP server

Local
github.com/huang-shScience & Education11Updated 76w ago
Repository

About Scanpy MCP server

An MCP server that makes Scanpy’s scRNA-seq data I/O, preprocessing, analysis, and plotting available through natural language. It is intended for researchers and agent developers calling Scanpy functions; the project is no longer maintained.

Key features

  1. 01Natural-language single-cell data I/O
  2. 02Filtering and quality control
  3. 03Normalization, scaling, and PCA
  4. 04Clustering and differential expression
  5. 05Violin, heatmap, and dot plots

Use cases

  1. 01Preprocess single-cell data with natural-language requests
  2. 02Analyze cell clusters and differential expression
  3. 03Call Scanpy functions from agent applications

MCP support

It exposes Scanpy data I/O, preprocessing, analysis, and plotting capabilities as tools for MCP clients. It can run locally or accept remote connections over HTTP transport.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project 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⚠️ Important Notice: This repository is no longer maintained.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

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

🏎️ 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([email protected]). Contributions to the code are also welcome!

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.