Ontology Lookup Service
The EMBL-EBI Ontology Lookup Service (OLS)
What is Ontology Lookup Service?
Ontology Lookup Service is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to embl-ebi ontology lookup service (ols)
The EMBL-EBI Ontology Lookup Service (OLS)
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- The EMBL-EBI Ontology Lookup Service (OLS)
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx ols4Configuration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Ontology Lookup Service
OLS4 is the fourth generation of the EMBL-EBI Ontology Lookup Service, providing a centralized repository and API for hundreds of biomedical ontologies — including Gene Ontology, EFO, HP, MONDO, and many others. It exposes a REST API and an MCP endpoint at https://www.ebi.ac.uk/ols4/api/mcp, allowing AI assistants to search, browse, and query ontology terms, hierarchies, and semantic relationships without leaving the chat interface. Researchers and bioinformaticians use OLS4 to annotate datasets with standardized ontology terms, explore concept hierarchies, and ensure data interoperability under FAIR principles.
Prerequisites
- An MCP client that supports Streamable HTTP transport (such as Claude Desktop or a custom MCP host)
- Internet access to reach https://www.ebi.ac.uk — no API key required for the public EBI endpoint
- For self-hosting: Docker and Docker Compose, plus at least 8 GB RAM for the PostgreSQL database
- For self-hosting: Python 3 for running the OpenLane dataloader script
Use the public EBI MCP endpoint (no installation required)
OLS4 provides a public MCP endpoint hosted at EBI that you can connect to directly without any local installation. This is the recommended approach for most users.
Configure your MCP client with the public endpoint
Add the OLS4 MCP server to your client configuration using the public Streamable HTTP URL.
{
"mcpServers": {
"ols4": {
"type": "http",
"url": "https://www.ebi.ac.uk/ols4/api/mcp"
}
}
}Self-host: Run the dataloader to build the database
If you need a private or customized instance, clone the OLS4 repository and run the dataloader with your chosen ontology config to populate the PostgreSQL database.
git clone https://github.com/EBISPOT/ols4
cd ols4
OLS4_CONFIG=./dataload/configs/efo.json ./dataload.shSelf-host: Start the full stack with Docker Compose
After the dataloader completes, bring up the API server and frontend using Docker Compose. The web UI will be available at http://localhost:8081.
docker compose upSelf-host: Add custom ontologies
To index your own OWL or RDFS files, create a JSON config following the EFO template in ./dataload/configs/ with relative paths to your ontology files, then re-run the dataloader.
Ontology Lookup Service Examples
Client configuration
Configuration using the public EBI OLS4 MCP endpoint via Streamable HTTP.
{
"mcpServers": {
"ols4": {
"type": "http",
"url": "https://www.ebi.ac.uk/ols4/api/mcp"
}
}
}Prompts to try
Example prompts to use with Claude once OLS4 is connected.
- "Search for ontology terms related to 'type 2 diabetes' across all available ontologies"
- "What are the child terms of the Gene Ontology term GO:0008150 (biological process)?"
- "Find the EFO term for 'breast carcinoma' and show its parent terms in the hierarchy"
- "List all ontologies available in OLS4 that cover phenotype data"
- "Fetch the definition and synonyms for HP:0001250 (Seizure) from the Human Phenotype Ontology"Troubleshooting Ontology Lookup Service
MCP client cannot connect to the public EBI endpoint
Verify your MCP client supports Streamable HTTP transport. Some older clients only support stdio or SSE. Check for network firewall rules that may block outbound HTTPS to ebi.ac.uk.
Self-hosted dataloader runs out of memory
The PostgreSQL database with pgvector for full-text and embedding search requires significant RAM (8 GB or more). Increase Docker's memory allocation in Docker Desktop preferences, or use a smaller ontology config for testing.
Custom ontology not appearing after dataloader run
Ensure your JSON config file uses relative paths to the OWL/RDFS files and that the files are accessible from the directory where you ran the dataloader script. Check the dataloader output logs for parsing errors.
Frequently Asked Questions about Ontology Lookup Service
What is Ontology Lookup Service?
Ontology Lookup Service is a Model Context Protocol (MCP) server that embl-ebi ontology lookup service (ols) It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Ontology Lookup Service?
Follow the installation instructions on the Ontology Lookup Service GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Ontology Lookup Service?
Ontology Lookup Service works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Ontology Lookup Service free to use?
Yes, Ontology Lookup Service is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Ontology Lookup Service Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Ontology Lookup Service? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Ontology Lookup Service in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Ontology Lookup Service?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.