mcpField
I
Infercnv-MCP

Infercnv-MCP

Local
github.com/scmcphubScience & Education2Updated 70w ago
Repository

About Infercnv-MCP

Infercnv-MCP provides a natural-language MCP interface to infercnvpy for CNV inference from scRNA-Seq data, aimed at researchers and agent developers. It covers data handling, preprocessing, inference scores, and visualizations.

Key features

  1. 01Read and write scRNA-Seq data and gene positions
  2. 02Compute neighbors and prepare data
  3. 03Infer CNVs and calculate scores
  4. 04Create chromosome heatmaps, UMAP, and t-SNE plots

Use cases

  1. 01Analyze CNVs in scRNA-Seq data using natural language
  2. 02Integrate CNV analysis into agent applications

MCP support

This MCP server exposes infercnvpy data handling, CNV analysis, and visualization tools to compatible AI clients, plugins, and agent frameworks.

#infercnv#cnv-analysis#scrna-seq

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

Infercnv-MCP

Natural language interface for Copy Number Variation (CNV) inference from scRNA-Seq data with infercnvpy through MCP.

🪩 What can it do?

  • IO module for reading and writing scRNA-Seq data, load gene position
  • Preprocessing module for neighbors computation and data preparation
  • Tool module for CNV inference, cnv score
  • Plotting module for chromosome heatmaps, UMAP, and t-SNE visualizations

❓ Who is this for?

  • Researchers who want to infer CNVs from scRNA-Seq data using natural language
  • Agent developers who want to integrate CNV analysis into their applications

🌐 Where to use it?

You can use infercnv-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

📚 Documentation

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

🏎️ Quickstart

Install

Install from PyPI

pip install infercnv-mcp

you can test it by running

infercnv-mcp run
run infercnv-mcp locally

Refer to the following configuration in your MCP client:

check path

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

"mcpServers": {
  "infercnv-mcp": {
    "command": "/home/test/bin/infercnv-mcp",
    "args": [
      "run"
    ]
  }
}
Run infercnv-server remotely

Refer to the following configuration in your MCP client:

Run it in your server

infercnv-mcp 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!

Citing

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

https://github.com/icbi-lab/infercnvpy

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.