OLS
A model context protocol (MCP) server for the EBI Ontology Lookup Service (OLS)
What is OLS?
OLS is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol (mcp) server for the ebi ontology lookup service (ols)
A model context protocol (MCP) server for the EBI Ontology Lookup Service (OLS)
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A model context protocol (MCP) server for the EBI Ontology L
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx olsConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use OLS
OLS MCP Server connects AI assistants to the European Bioinformatics Institute's Ontology Lookup Service (OLS), a curated repository of hundreds of life-science ontologies including the Gene Ontology, Human Phenotype Ontology, and many others. It exposes seven tools for searching ontology terms, retrieving term metadata, navigating ontology hierarchies (children and ancestors), discovering available ontologies, and finding semantically similar terms using LLM embeddings. Bioinformaticians, life-science researchers, and developers working with biological data can use this server to query and explore structured biological knowledge directly from their AI assistant.
Prerequisites
- Python 3.8+ and the uv package manager installed
- Internet access to reach the EBI OLS API at https://www.ebi.ac.uk/ols4
- No API key required — the EBI OLS API is publicly accessible
- An MCP-compatible client such as Claude Desktop
Install uv package manager
Install the uv package manager which is required to run the ols-mcp-server.
# macOS/Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
# Windows
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"Clone and set up the server
Clone the ols-mcp-server repository and synchronize its dependencies using uv.
git clone https://github.com/seandavi/ols-mcp-server.git
cd ols-mcp-server
uv syncOptionally install as a uv tool
Install ols-mcp-server as a globally available uv tool for easier MCP client configuration.
uv tool install .Configure your MCP client
Add the ols-mcp-server to your Claude Desktop configuration using uv tool run. No environment variables or API keys are needed.
Test the connection
Ask Claude to search for a common biological term to confirm the server is connected and the EBI OLS API is reachable.
OLS Examples
Client configuration
Add ols-mcp-server to Claude Desktop using uv tool run. No API keys or environment variables are required.
{
"mcpServers": {
"ols-mcp-server": {
"command": "uv",
"args": ["tool", "run", "ols-mcp-server"],
"env": {}
}
}
}Prompts to try
Query biological ontologies and navigate term hierarchies using natural language.
- "Search for terms related to diabetes in the Human Phenotype Ontology."
- "Find all terms containing 'apoptosis' in the Gene Ontology."
- "Tell me about the Gene Ontology — its scope and how many terms it contains."
- "Show me the children of the term 'metabolic process' in GO."
- "What are the ancestor terms of 'type 2 diabetes' in the Human Phenotype Ontology?"
- "Find terms semantically similar to 'programmed cell death'."Troubleshooting OLS
Server starts but search returns no results
Verify that the EBI OLS API is reachable from your machine by running 'curl https://www.ebi.ac.uk/ols4/api'. If behind a corporate firewall or VPN, ensure outbound HTTPS to ebi.ac.uk is permitted.
uv tool run command not found after installation
Ensure uv is on your PATH by running 'which uv'. If not found, follow the uv post-install instructions to add ~/.cargo/bin or the uv binary directory to your shell PATH and restart your terminal.
Ontology term searches return unexpected results or wrong ontology
The OLS search spans all ontologies by default. Specify the ontology in your prompt (e.g., 'in the Gene Ontology' or 'in HPO') so the server can filter results to the correct ontology.
Frequently Asked Questions about OLS
What is OLS?
OLS is a Model Context Protocol (MCP) server that model context protocol (mcp) server for the ebi ontology lookup service (ols) It connects AI assistants to external tools and data sources through a standardized interface.
How do I install OLS?
Follow the installation instructions on the OLS GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with OLS?
OLS works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is OLS free to use?
Yes, OLS is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
OLS Alternatives — Similar Data Science & ML Servers
Looking for alternatives to OLS? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up OLS 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 OLS?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.