MCP Server: Galaxy Tool Utilities

by goeckslab

1 stars
337 downloads
Not rated
GitHub

About

MCP Server: Galaxy Tool Utilities is an MCP server that exposes utilities for working with Galaxy tool XML files. It allows users to validate Galaxy tool XML against the official schema and generate boilerplate templates. It is intended for use with MCP-compatible agents such as…

Details

Author
goeckslab
GitHub stars
1
Downloads
337
Categories
Other

- Validate Galaxy tool XML files against the official schema.
- Generate a basic boilerplate Galaxy tool XML template.
- Easy integration with Cline and other MCP-compatible agents.
- Uses the standard stdio transport.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name MCP Server: Galaxy Tool Utilities
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Clone the repository, install dependencies with uv sync, then add the server to your Cline MCP configuration (using uv as the command and pointing to the repository directory). Once configured, you can invoke it via Cline with prompts like "Create a Galaxy tool that uses PyCaret to perform regression on tabular data."

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "mcp server: galaxy tool utilities": {
            "mcp-server-galaxy-tool": {
                "command": "uv",
                "args": [
                    "sync"
                ]
            }
        }
    }
}

McpServers

{
    "mcp-server-galaxy-tool": {
        "command": "uv",
        "args": [
            "sync"
        ]
    }
}

MCP Server: Galaxy Tool Utilities

This project provides an MCP (Model Context Protocol) server that exposes utilities for working with Galaxy tool XML files.

Features (More Coming Soon)

- Validate Galaxy Tool XML: Check if a Galaxy tool XML file is valid according to the official schema.
- Generate Basic Template: Instantly create a boilerplate Galaxy tool XML file.

Requirements

- Python 3.8+
- uv (for running the server, or use your preferred Python environment)
- Cline (or any MCP-compatible agent)

Installation

1. Clone this repository:

   git clone https://github.com/yourusername/mcp-server-galaxy-tool.git
cd mcp-server-galaxy-tool

2. Install dependencies:

   uv sync

Configuring the MCP Server in Cline

To use this MCP server with Cline in VSCode, add it to your Cline MCP configuration. Here’s how:

1. Install Cline in VSCode by searching for it in the Extensions marketplace and installing it.

2. Follow the Cline documentation to add a new server entry. Here is an example MCP servers config:

   {
     "mcpServers": {
       "Galaxy Tools": {
         "disabled": false,
         "timeout": 60,
         "command": "<path to your uv>",
         "args": [
           "--directory",
           "</path/to/this/repo/mcp-server-galaxy-tool>",
           "run",
           "main.py"
         ],
         "transportType": "stdio"
       }
     }
   }
   

- Make sure the command and workingDirectory match your local setup.
- Save the file and restart Cline if necessary.

Usage

Once the server is running and configured in Cline, you can try this example in Cline:

Create a Galaxy tool that uses PyCaret to perform regression on tabular data.

Project Structure

- main.py — MCP server entry point
- galaxy.xsd — Official Galaxy tool XML schema
- pyproject.toml — Python project configuration
- README.md — This documentation

License

MIT License

Acknowledgments

- Galaxy Project
- Model Context Protocol (MCP)
- Cline

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.