{
  "markdown": "# Galaxy MCP Server\n\nThis 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.\n\n## Project Overview\n\nThis repository contains a Python-based MCP server implementation that provides comprehensive integration with Galaxy's API through BioBlend.\n\nIn addition to the Python server, this repository now includes a **TypeScript\nworkspace** in [`galaxy-agent-tools/`](galaxy-agent-tools/) that offers the same\nGalaxy operations two ways: a `galaxy-cli` command-line tool and a `galaxy-mcp`\n(Node) MCP server, built on a shared core and kept in lockstep with this server's\ntoolset. See the [galaxy-agent-tools README](galaxy-agent-tools/README.md) to build\nand use it.\n\n## Key Features\n\n- **Galaxy Connection**: Connect to any Galaxy instance with a URL and API key\n- **OAuth Login (optional)**: Offer browser-based sign-in that exchanges credentials for temporary Galaxy API keys\n- **Server Information**: Retrieve comprehensive server details including version, configuration, and capabilities\n- **Tools Management**: Search, view details, and execute Galaxy tools\n- **Workflow Integration**: Access and import workflows from the Interactive Workflow Composer (IWC)\n- **History Operations**: Manage Galaxy histories and datasets\n- **File Management**: Upload files to Galaxy from local storage\n- **Comprehensive Testing**: Full test suite with mock-based testing for reliability\n\n## Quick Start\n\nThe `galaxy-mcp` CLI ships with both stdio (local) and HTTP transports. Choose the setup that\nmatches your client:\n\n```bash\n# Stdio transport (default) – great for local development tools\nuvx galaxy-mcp\n\n# HTTP transport with OAuth (for remote/browser clients)\nexport GALAXY_URL=\"https://usegalaxy.org.au/\"          # Target Galaxy instance\nexport GALAXY_MCP_PUBLIC_URL=\"https://mcp.example.com\" # Public base URL for OAuth redirects\nexport GALAXY_MCP_SESSION_SECRET=\"$(openssl rand -hex 32)\"\nuvx galaxy-mcp --transport streamable-http --host 0.0.0.0 --port 8000\n```\n\nWhen running over stdio you can provide long-lived credentials via environment variables:\n\n```bash\nexport GALAXY_URL=\"https://usegalaxy.org/\"\nexport GALAXY_API_KEY=\"your-api-key\"\n```\n\nFor OAuth flows the server exchanges user credentials for short-lived Galaxy API keys on demand, so\nyou typically leave `GALAXY_API_KEY` unset.\n\nFor non-OAuth HTTP clients, `connect(url=..., api_key=...)` stores Galaxy credentials per MCP\nsession rather than globally. Clients normally preserve MCP sessions by default, which allows\nmultiple users to share the same MCP server while keeping their Galaxy credentials isolated.\n\n### Alternative Installation\n\n```bash\n# Install from PyPI\npip install galaxy-mcp\n\n# Run (stdio by default)\ngalaxy-mcp\n\n# Or from source using uv\ncd mcp-server-galaxy-py\nuv sync\nuv run galaxy-mcp --transport streamable-http --host 0.0.0.0 --port 8000\n```\n\n## Container Usage\n\nThe published image defaults to stdio transport (no HTTP listener):\n\n```bash\ndocker run --rm -it \\\n  -e GALAXY_URL=\"https://usegalaxy.org/\" \\\n  -e GALAXY_API_KEY=\"your-api-key\" \\\n  galaxyproject/galaxy-mcp\n```\n\nFor OAuth + HTTP:\n\n```bash\ndocker run --rm -it -p 8000:8000 \\\n  -e GALAXY_URL=\"https://usegalaxy.org.au/\" \\\n  -e GALAXY_MCP_TRANSPORT=\"streamable-http\" \\\n  -e GALAXY_MCP_PUBLIC_URL=\"https://mcp.example.com\" \\\n  -e GALAXY_MCP_SESSION_SECRET=\"$(openssl rand -hex 32)\" \\\n  galaxyproject/galaxy-mcp\n```\n\n## Connect to Claude Desktop\n- Ensure that GalaxyMCP runs with `uvx galaxy-mcp`\n- Add `export GALAXY_SERVER=https://usegalaxy.org` to your .bashrc (or equiv)\n- Download and install [claude desktop](https://www.claude.com/download)\n- Go to Settings -> Developer -> Edit Config\n- Add this to `claude_desktop_config.json`\n```\n{\n  \"mcpServers\": {\n    \"galaxy-mcp\": {\n      \"command\": \"uvx\",\n      \"args\": [\"galaxy-mcp\"],\n      \"env\": {\n        \"GALAXY_URL\": \"https://usegalaxy.org\",\n        \"GALAXY_API_KEY\": \"SECRETS\"\n      }\n    }\n  }\n}\n```\n- Under the developer menu, you should now see `galaxy-mcp` as running (you may need to restart Claude desktop)\n- Prompt Claude with \"can you connect to galaxy\"\n- 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\"\n- Talk to Claude to work with your galaxy instance, e.g. \"give a summary with my histories\"\n\n## Development Guidelines\n\nSee the [Python implementation README](mcp-server-galaxy-py/README.md) for specific instructions and documentation.\n\n## License\n\n[MIT](LICENSE)\n",
  "bytes": 4698,
  "sha": "d8bb3414339f66c406755d8d07ca7bca8191f4deab83cf5f1c913da1bc98263c",
  "repo_slug": "galaxyproject/galaxy-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_galaxyproject_galaxy_mcp_94e32871/readme"
}