GeneOntology
A comprehensive Model Context Protocol server for accessing Gene Ontology (GO) data, enabling AI systems to perform ontology-based analysis, gene annotation research, and functional enrichment studies.
claude mcp add --transport stdio augmented-nature-geneontology-mcp-server node /path/to/go-server/build/index.js
How to use
This MCP server provides access to Gene Ontology (GO) data, enabling AI systems to perform ontology-based analysis, gene annotation retrieval, and term validation. It exposes tools for searching GO terms, fetching detailed term information, validating GO identifiers, and obtaining ontology-wide statistics. Use the go-server entry in your MCP client configuration to connect, then invoke the provided tools (search_go_terms, get_go_term, validate_go_id, and get_ontology_stats) to interact with GO data. The resource templates (go://term, go://annotations, go://search, go://hierarchy) help standardize how you request data and navigate the ontology hierarchy.
How to install
Prerequisites:
- Node.js and npm installed on your system.
Install and build:
- git clone <repository-url> // if you haven't already
- cd GeneOntology-MCP-Server
- npm install
- npm run build
Run locally (example):
- Ensure you have a Node environment and that build/index.js exists after npm run build.
- Start the server as part of your MCP network configuration, for example by launching the MCP bridge or wrapper that loads the built index.js entry point.
Notes:
- The server expects to be accessed via the MCP protocol through the configured command and path (see mcp_config).
Additional notes
Tips and common issues:
- Ensure the build output path matches the path used in the mcp_config (index.js under build is typical after npm run build).
- If GO data sources require credentials or API keys (e.g., QuickGO), set the appropriate environment variables as needed by your deployment (not detailed in this README).
- Validate GO IDs using validate_go_id to quickly catch malformed identifiers before querying detailed term data.
- Monitor for API rate limits if the server relies on external services (QuickGO/GO Consortium) and implement retry/backoff as needed in your client.
- If you modify data sources or endpoints, update get_ontology_stats and related documentation to reflect new statistics or fields.
Environment variable placeholder examples (if needed):
- GO_API_KEY=your-quickgo-api-key
- GO_BASE_URL=https://www.ebi.ac.uk/QuickGO/api
Configuration tip: keep the mcpServers entry consistent with your MCP infrastructure naming conventions (e.g., server-name: go-server).
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.