Galaxy

Bridges Galaxy with MCP clients to search tools, run tools, manage histories, and import workflows.

python

19

GitHub Stars

python

Language

4 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

{
  "mcpServers": {
    "galaxyproject-galaxy-mcp": {
      "command": "uvx",
      "args": [
        "galaxy-mcp"
      ],
      "env": {
        "GALAXY_URL": "https://usegalaxy.org/",
        "GALAXY_API_KEY": "YOUR_API_KEY",
        "GALAXY_MCP_PUBLIC_URL": "https://mcp.example.com",
        "GALAXY_MCP_SESSION_SECRET": "YOUR_SESSION_SECRET"
      }
    }
  }
}

You can run a Model Context Protocol (MCP) server that connects to Galaxy, enabling you to search and execute Galaxy tools, manage histories, import workflows, and upload files. This MCP server acts as a bridge between clients and Galaxy, making common Galaxy actions programmable and accessible from AI assistants and other tools.

How to use

To use the Galaxy MCP server, run it locally and connect your MCP client to it. The standard, local transport runs inside your development environment, while the HTTP transport enables remote clients and browser-based flows with OAuth. You can perform common tasks such as searching for tools, inspecting tool details, executing tools with inputs, importing workflows, and handling histories and file uploads.

How to install

Prerequisites: you need Python installed to run the MCP server locally. You also need the uvx runtime for the provided CLI usage. You may optionally use Docker for containerized deployment.

# Install from PyPI
pip install galaxy-mcp

# Run (stdio by default)
galaxy-mcp

# Or run via the uvx runner if you prefer local development tooling
uvx galaxy-mcp

Additional configuration and usage notes

When running over stdio, you can provide long-lived Galaxy credentials via environment variables. This enables direct access to a Galaxy instance without requiring an interactive login each time.

export GALAXY_URL="https://usegalaxy.org/"
export GALAXY_API_KEY="your-api-key"
uvx galaxy-mcp

Available tools

search_tools

Search available Galaxy tools across toolsheds and histories to identify suitable tools for your analysis.

view_tool_details

Retrieve detailed information about a Galaxy tool, including inputs, outputs, and parameters.

execute_tool

Execute a selected Galaxy tool with specified inputs and dataset references.

import_workflows

Import workflows from the Interactive Workflow Composer (IWC) to reuse complex analyses.

manage_histories

Create, view, and organize Galaxy histories and manage datasets within those histories.

upload_files

Upload files from local storage into Galaxy for use as inputs to tools or workflows.