Liana-MCP

Provides a natural language interface to run Liana functions for scRNA-Seq analysis via MCP, including IO, cell-cell communication, and plotting.

python

2

GitHub Stars

python

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

Liana-MCP provides a natural language interface to run Liana’s scRNA-Seq analysis capabilities through MCP, enabling seamless IO, cell–cell communication analysis, and plotting from any MCP-enabled client.

How to use

Set up your MCP client to connect to Liana-MCP using either a local (stdio) server or a remote HTTP server. The local option runs the MCP server on your machine and exposes a standard input/output interface, while the remote option starts a server that you reach over HTTP.

How to install

Prerequisites: Python installed on your system.

Install the MCP server package from PyPI.

Test that the MCP server runs locally.

Run the MCP server remotely and connect your MCP client to it.

Configuration and usage examples

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

{
  "mcpServers": {
    "liana_mcp": {
      "url": "http://localhost:8000/mcp"
    }
  }
}

Additional notes

Install commands and runtime examples include both local (stdio) and remote (http) configurations. The local setup runs the MCP server directly, while the remote setup exposes the server over HTTP for your MCP client to connect to.

Available tools

io_module

IO module to read and write scRNA-Seq data.

cell_communication

Cell-cell communication inference method.

plot_circle

Circle plot visualization.

plot_dot

Dot plot visualization.