Scanpy MCP server

SCMCP is an MCP server that enables natural language-based analysis of single-cell RNA sequencing (scRNA-Seq) data. It provides a bridge between natural language commands and Scanpy functionality, allowing researchers to perform complex scRNA-Seq analyses through simple, conversational interactions rather than writing code.

Installation

You can install SCMCP from PyPI using pip:

pip install scmcp

After installation, you can verify that it's working by running:

scmcp run

Usage

SCMCP can be used both locally and remotely, depending on your needs.

Running Locally

To run SCMCP on your local machine, configure your MCP client with the following settings:

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

Running Remotely

To run SCMCP on a remote server, execute the following command on your server:

scmcp run --transport sse --port 8000

Then, configure your MCP client using the server's URL:

http://localhost:8000/sse

Replace localhost with your server's actual address if accessing from a different machine.

Features

SCMCP provides natural language interfaces to various scRNA-Seq analysis tasks:

• Data I/O: Read and write scRNA-Seq data using natural language
• Preprocessing: Perform filtering, quality control, normalization, scaling, identify highly-variable genes, PCA, and create neighbor graphs
• Analysis Tools: Run clustering and differential expression analyses
• Visualization: Create violin plots, heatmaps, and dot plots
• Cell-Cell Communication: Analyze interactions between cells

Compatible Platforms

SCMCP works with any AI client, plugin, or agent framework that supports the Model Context Protocol (MCP), including:

• AI clients like Cherry Studio
• Plugins like Cline
• Agent frameworks like Agno

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.