BioOntology

The BioOntology MCP Server exposes a range of tools to search, annotate, and explore biological ontologies via the MCP protocol. It connects to BioPortal-backed ontologies (over 1,200) and provides capabilities such as search_terms for querying ontology terms with filters, annotate_text for linking text to relevant ontology concepts, and batch_annotate for processing multiple texts efficiently. Other utilities include get_class_info for ontology class details, get_ontology_info and get_ontology_metrics for metadata and usage analytics, and recommendations to suggest relevant ontologies based on input text or keywords. Resource templates like bioontology://ontology/{acronym}, bioontology://class/{ontology}/{class_id}, and bioontology://annotations/{text} enable direct data access via MCP-compatible clients. To use the server, connect with an MCP client and invoke the desired tool with the appropriate arguments (for example, search_terms, annotate_text, or batch_annotate). The MCP configuration example shows how to wire the server into your client config, including the required API key environment variable.

Prerequisites:

• Node.js and npm installed on your system
• Access to a BioOntology API key from BioPortal

Installation steps:

1. Clone the repository or download the server package.
2. Install dependencies: npm install
3. Build the server (if a build step is present): npm run build
4. Run the server (example): node build/index.js

Configuration (environment):

• Ensure you have a BioOntology API key and set it as an environment variable: export BIOONTOLOGY_API_KEY=your_api_key_here

Usage with MCP:

• Integrate the server into your MCP client configuration as shown in the README, ensuring the BIOONTOLOGY_API_KEY is supplied via the environment.

Tips and notes:

• Keep your BIOONTOLOGY_API_KEY secure; do not commit it to version control.
• The server communicates via MCP; ensure your MCP client is configured to point to the server and uses the same tool names (e.g., search_terms, annotate_text).
• If you encounter API rate limits, consider batching requests or implementing client-side throttling.
• Monitor for any required upgrades to the BioPortal API or ontology sets; the server may need redeployment with updated dependencies.
• Validate inputs thoroughly; the server provides parameter validation and helpful error messages for invalid requests.