What Galaxy instance can I connect to?

Any Galaxy instance you have network access to and valid credentials for. Set GALAXY_URL to your instance URL (e.g., https://usegalaxy.org) and provide a GALAXY_API_KEY for authentication.

How do I get a Galaxy API key?

Log into your Galaxy instance, go to User > Preferences > Manage API Key, and generate a new key. Store it securely and pass it to the MCP server via the GALAXY_API_KEY environment variable.

Can I run existing Galaxy workflows?

Yes. The server can execute tools and manage workflows on your Galaxy instance. Refer to the Galaxy API documentation for workflow invocation details and supported parameters.

What bioinformatics tools are available?

Any tool installed in your Galaxy instance is available. Common tools include FastQC, BWA, GATK, and thousands of others from the Galaxy ToolShed. Use the server to list tools dynamically.

Do I need to install Galaxy locally?

No. You connect to an existing Galaxy instance via its URL and API key. The MCP server communicates remotely—no local Galaxy installation required.

MCP ServerSTDIOOfficialv1.3.0

Galaxy MCP Server

Execute bioinformatics tools and manage workflows on a Galaxy instance via API. For developers integrating Galaxy automation into AI agents or building programmatic analysis pipelines.

io.github.galaxyproject/galaxy-mcp

Try MCP with AI models View source

Hosted URL

Local install

Transport

STDIO

Auth

2 required env vars

What the Galaxy MCP server does

How models use it and what it is built for.

Execute bioinformatics tools and manage workflows on a Galaxy instance via API. For developers integrating Galaxy automation into AI agents or building programmatic analysis pipelines.

Connect to Galaxy

Local install — runs as a subprocess.

uvx galaxy-mcp==1.3.0

Environment variables

Configuration this server reads at startup.

GALAXY_URLRequired
URL of the Galaxy instance to connect to (e.g., https://usegalaxy.org)
GALAXY_API_KEYRequiredSecret
API key for authenticating with the Galaxy instance

Resources

Where to find authoritative docs and source for Galaxy.

Source repository

Example prompts for Galaxy

Paste any of these into Agent Studio after connecting Galaxy.

List all available tools in my Galaxy instance and their input parameters
Execute a FastQC quality control tool on dataset ID 12345
Create and run a workflow that maps reads then calls variants
Show the status and output files from job ID abc123def456

Galaxy MCP server — FAQ

Common questions about connecting and running Galaxy.

What Galaxy instance can I connect to?
Any Galaxy instance you have network access to and valid credentials for. Set GALAXY_URL to your instance URL (e.g., https://usegalaxy.org) and provide a GALAXY_API_KEY for authentication.
How do I get a Galaxy API key?
Log into your Galaxy instance, go to User > Preferences > Manage API Key, and generate a new key. Store it securely and pass it to the MCP server via the GALAXY_API_KEY environment variable.
Can I run existing Galaxy workflows?
Yes. The server can execute tools and manage workflows on your Galaxy instance. Refer to the Galaxy API documentation for workflow invocation details and supported parameters.
What bioinformatics tools are available?
Any tool installed in your Galaxy instance is available. Common tools include FastQC, BWA, GATK, and thousands of others from the Galaxy ToolShed. Use the server to list tools dynamically.
Do I need to install Galaxy locally?
No. You connect to an existing Galaxy instance via its URL and API key. The MCP server communicates remotely—no local Galaxy installation required.

Skip the local setup — run MCP in your browser

MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.

Open Agent Studio