
Galaxy Mcp
io.github.galaxyprojectPublished by GitHub account galaxyprojectv1.3.0Updated Oct 24, 2026
MCP server for Galaxy bioinformatics platform - connect, execute tools, and manage workflows
Overview
A local MCP server that connects an assistant to a Galaxy bioinformatics instance to search and run tools, manage workflows, histories and files.
- What you can do
- Connect to a Galaxy instance and read server version, configuration and capabilities, with optional OAuth sign-in for temporary API keys. Search the tool catalog, inspect tool inputs and execute Galaxy tools, including creating, listing, running and deactivating user-defined tools. Find and import workflows from the Intergalactic Workflow Commission, invoke them and follow their invocations. Manage histories, datasets, collections and the jobs behind them, and upload files from local storage or a URL and download results. Read and write Galaxy-flavored markdown pages with revision history, and optionally resolve verified BioContainers images for conda packages.
- When to use it
- Useful when you work on the Galaxy bioinformatics platform and want an assistant to drive tool runs, workflows, histories and datasets from a chat client instead of the web interface. Also suited to authoring and testing user-defined tools and to importing published workflows.
- Requirements
- Runs locally as a Python package (galaxy-mcp) via uvx or pip, or as a published container image. Requires GALAXY_URL pointing at a Galaxy instance and, for stdio use, GALAXY_API_KEY; OAuth HTTP mode instead needs GALAXY_MCP_PUBLIC_URL and a stored GALAXY_MCP_SESSION_SECRET. Network access to the Galaxy instance is required. Optional extras add container recommendation and code mode.
Installation
In SourceWeft
- Open Galaxy Mcp in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
Galaxy MCP Server
This project provides a Model Context Protocol (MCP) server for interacting with the Galaxy bioinformatics platform. It enables AI assistants and other clients to connect to Galaxy instances, search and execute tools, manage workflows, and access other features of the Galaxy ecosystem.
Project Overview
The repository holds two independent implementations of the same Galaxy operation set, and the contract that keeps them in step:
python/-- the Python MCP server, published to PyPI asgalaxy-mcp. It reaches Galaxy through BioBlend. See the Python README.typescript/-- a pnpm workspace published to npm as@galaxyproject/galaxy-ops,galaxy-cliandgalaxy-mcp: one framework-free core (galaxy-ops) with a command line and a stdio MCP server on top. See the TypeScript README.contract/-- what both are held to: the Python surface manifest, golden results replayed through both, the snapshot of Galaxy's built-in server, and the registry of known differences. See the contract README.
The two are meant to stay in step: an operation keeps its name and its meaning across both. They are still separate codebases with separate release trains, though, so each README lists the operations that surface actually has -- read the one you are using.
ROADMAP.md explains why there are two implementations, how they relate to Galaxy's built-in MCP server, and what comes next. PARITY.md is the generated, CI-checked record of where they differ.
Key Features
- Galaxy Connection: Connect to any Galaxy instance with a URL and API key
- OAuth Login (optional): Offer browser-based sign-in that exchanges credentials for temporary Galaxy API keys
- Server Information: Retrieve comprehensive server details including version, configuration, and capabilities
- Tools Management: Search the tool catalog, inspect a tool's inputs, and execute Galaxy tools
- User-Defined Tools: Create, list, run, and deactivate unprivileged user-defined tools
- Workflow Integration: Find and import workflows from the Intergalactic Workflow Commission (IWC), then invoke them and follow their invocations
- History Operations: Manage Galaxy histories, datasets, and collections, and inspect the jobs behind them
- File Management: Upload files to Galaxy from local storage or from a URL, and download results back
- Pages: Read and write Galaxy-flavored markdown pages -- history-attached notebooks and standalone reports -- including their revision history
- Verified Container Recommendation (optional): Resolve a real
quay.io/biocontainersimage for a set of conda packages instead of guessing one -- see Optional extras - Mock-based test suite: The default suite runs entirely against mocked Galaxy responses, so it needs no server; a separate suite against a live Galaxy is opt-in and skips when no credentials are configured
Optional extras
container-recommend
Enables the recommend_biocontainer tool, which resolves a verified
quay.io/biocontainers image for a set of conda packages. Authoring a user-defined
tool means naming a container, and a hallucinated image tag is the most common way a
UDT passes validation and then dies at run time with manifest unknown. This wraps
galaxy.tool_util.deps.mulled.recommend -- the same resolver Galaxy's own custom-tool
agent uses (added in Galaxy 26.1, galaxyproject/galaxy#22981) -- so the image is
checked against quay.io rather than invented.
It is an extra rather than a hard dependency because galaxy-tool-util pulls in lxml
and conda-package-streaming, and every other tool on this server works without it. The
tool is only registered when the extra is installed, so a stock install simply
doesn't advertise it.
The same resolver is also available as a standalone CLI once installed:
mulled-recommend samtools=1.17.
code-mode
Collapses the whole tool catalog into three meta-tools -- search, get_schema, and
run_galaxy_tool -- so an agent pays for a tool's schema only when it decides to use it.
The extra pulls in pydantic-monty, the sandboxed interpreter that runs the submitted
code. Without the extra the server still starts, but asking for code mode is an error
rather than a silent downgrade.
See Tool discovery mode in the Python README for what the trade-off buys you.
Quick Start
The galaxy-mcp CLI ships with both stdio (local) and HTTP transports. Choose the setup that
matches your client:
When running over stdio you can provide long-lived credentials via environment variables:
For OAuth flows the server exchanges user credentials for short-lived Galaxy API keys on demand, so
you typically leave GALAXY_API_KEY unset.
For non-OAuth HTTP clients, connect(url=..., api_key=...) stores Galaxy credentials per MCP
session rather than globally, for a URL the operator allowed (GALAXY_URL or
GALAXY_MCP_EXTRA_ALLOWED_URLS). That keeps sessions apart but is not authentication: the HTTP
transports bind to 127.0.0.1 by default, refuse to serve a non-loopback address without OAuth
unless you pass --allow-unauthenticated, and disable the tools that touch the server's
filesystem. See Serving over HTTP.
Alternative Installation
Container Usage
Images are published to the GitHub Container Registry as
ghcr.io/galaxyproject/galaxy-mcp.
Use :latest (default) or pin a release, e.g. :1.10.0.
The published image defaults to stdio transport (no HTTP listener):
For OAuth + HTTP:
Connect to Claude Desktop
- Ensure that GalaxyMCP runs with
uvx galaxy-mcp - Add
export GALAXY_URL=https://usegalaxy.orgto your .bashrc (or equiv) - Download and install claude desktop
- Go to Settings -> Developer -> Edit Config
- Add this to
claude_desktop_config.json
- Under the developer menu, you should now see
galaxy-mcpas running (you may need to restart Claude desktop) - Prompt Claude with "can you connect to galaxy"
- If you have not provided the optional env config you'll be asked for connection details which you can provide like "Use my Galaxy API key: XXXXXXX"
- Talk to Claude to work with your galaxy instance, e.g. "give a summary with my histories"
Development Guidelines
See the Python implementation README for specific instructions and documentation.
License
Source: README.md at commit ee870af
Tools
0Version history
1- v1.3.0LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts