Galaxy Mcp

io.github.galaxyproject由 GitHub 账号 galaxyproject 发布v1.3.0更新于 Oct 24, 2026

MCP server for Galaxy bioinformatics platform - connect, execute tools, and manage workflows

概览

AI 生成的概览

一个本地 MCP 服务器,让助手连接 Galaxy 生物信息学平台,搜索并运行工具、管理工作流、历史记录和文件。

可以做什么
连接 Galaxy 实例,读取服务器版本、配置与能力,并可选通过 OAuth 登录换取临时 API 密钥。搜索工具目录、查看工具输入并执行 Galaxy 工具,包括创建、列出、运行和停用用户自定义工具。从 Intergalactic Workflow Commission 查找并导入工作流,调用工作流并跟踪其运行记录。管理历史记录、数据集、集合及其背后的作业,从本地或网址上传文件并下载结果。读写 Galaxy 风格的 markdown 页面及其修订历史,可选为 conda 软件包解析经过验证的 BioContainers 镜像。
适用场景
适合在 Galaxy 生物信息学平台上工作、希望用对话客户端而非网页界面来驱动工具运行、工作流、历史记录和数据集的人。也适合编写和测试用户自定义工具,以及导入已发布的工作流。
运行要求
以 Python 包(galaxy-mcp)通过 uvx 或 pip 本地运行,也可使用已发布的容器镜像。需要 GALAXY_URL 指向 Galaxy 实例,stdio 方式还需 GALAXY_API_KEY;OAuth 的 HTTP 模式则需要 GALAXY_MCP_PUBLIC_URL 和预先保存的 GALAXY_MCP_SESSION_SECRET。需要能访问 Galaxy 实例的网络。可选附加组件提供容器推荐和代码模式。
安装前请注意
GALAXY_API_KEY 和 GALAXY_MCP_SESSION_SECRET 属于机密;会话密钥须在重启后保持不变,否则此前签发的令牌将失效。该服务器可执行工具、运行工作流、上传下载文件并写入页面,会改动 Galaxy 账户中的数据。HTTP 传输本身不构成身份验证;默认只绑定回环地址,未启用 OAuth 时除非显式允许,否则拒绝非回环地址。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Galaxy Mcp,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

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 as galaxy-mcp. It reaches Galaxy through BioBlend. See the Python README.
  • typescript/ -- a pnpm workspace published to npm as @galaxyproject/galaxy-ops, galaxy-cli and galaxy-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/biocontainers image 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.

bash
uvx --from 'galaxy-mcp[container-recommend]' galaxy-mcp# or, for a local checkout:cd python && uv sync --extra container-recommend

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.

bash
uvx --from 'galaxy-mcp[code-mode]' galaxy-mcp --discovery-mode code

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:

bash
# Stdio transport (default) – great for local development toolsuvx galaxy-mcp
# HTTP transport with OAuth (for remote/browser clients)# Generate the session secret ONCE (`openssl rand -hex 32`) and store it. Every# restart and every replica must use the same value, or tokens issued earlier --# or by another replica -- stop decrypting.export GALAXY_URL="https://usegalaxy.org.au/"          # Target Galaxy instanceexport GALAXY_MCP_PUBLIC_URL="https://mcp.example.com" # Public base URL for OAuth redirectsexport GALAXY_MCP_SESSION_SECRET="<your stored secret>"uvx galaxy-mcp --transport streamable-http --host 0.0.0.0 --port 8000

When running over stdio you can provide long-lived credentials via environment variables:

bash
export GALAXY_URL="https://usegalaxy.org/"export GALAXY_API_KEY="your-api-key"

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

bash
# Install from PyPIpip install galaxy-mcp
# Run (stdio by default)galaxy-mcp
# Or from source using uvcd pythonuv syncuv run galaxy-mcp --transport streamable-http --port 8000

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):

bash
docker run --rm -it \  -e GALAXY_URL="https://usegalaxy.org/" \  -e GALAXY_API_KEY="your-api-key" \  ghcr.io/galaxyproject/galaxy-mcp

For OAuth + HTTP:

bash
# Generate once and keep it -- do NOT inline `openssl rand` here, or each# container start mints a key that invalidates every token issued before it.export GALAXY_MCP_SESSION_SECRET="<your stored secret>"
docker run --rm -it -p 8000:8000 \  -e GALAXY_URL="https://usegalaxy.org.au/" \  -e GALAXY_MCP_TRANSPORT="streamable-http" \  -e GALAXY_MCP_PUBLIC_URL="https://mcp.example.com" \  -e GALAXY_MCP_SESSION_SECRET \  ghcr.io/galaxyproject/galaxy-mcp

Connect to Claude Desktop

  • Ensure that GalaxyMCP runs with uvx galaxy-mcp
  • Add export GALAXY_URL=https://usegalaxy.org to your .bashrc (or equiv)
  • Download and install claude desktop
  • Go to Settings -> Developer -> Edit Config
  • Add this to claude_desktop_config.json
{  "mcpServers": {    "galaxy-mcp": {      "command": "uvx",      "args": ["galaxy-mcp"],      "env": {        "GALAXY_URL": "https://usegalaxy.org",        "GALAXY_API_KEY": "SECRETS"      }    }  }}
  • Under the developer menu, you should now see galaxy-mcp as 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

MIT

来源:README.md,提交 ee870af

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v1.3.0最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分