ols-mcp

# ols-mcp A Model Context Protocol (MCP) server for retrieving information from the Ontology Lookup Service (OLS). This package provides tools for searching ontologies, retrieving ontology details, and accessing ontology terms through a standardized MCP interface. ## Installation ### From PyPI ```bash pip install ols-mcp ``` ### From Source ```bash # Clone the repository git clone https://github.com/contextualizer-ai/ols-mcp.git cd ols-mcp # Install with uv (recommended) uv sync --group dev # Or with pip pip install -e . ``` ## Usage ### As MCP Server The primary use case is as an MCP server that provides ontology search capabilities to AI agents and applications. #### Claude Desktop Integration Add to your Claude Desktop configuration (`~/Library/Application Support/Claude/claude_desktop_config.json`): ```json { "mcpServers": { "ols-mcp": { "command": "ols-mcp", "args": [] } } } ``` #### Claude Code Integration ```bash claude mcp add ols-mcp ``` #### Goose Integration ```bash goose session start --with-mcp "ols-mcp" ``` ### Available Tools The MCP server provides three main tools: 1. **`search_all_ontologies`** - Search across all ontologies in OLS 2. **`get_ontology_info`** - Get detailed information about a specific ontology 3. **`get_terms_from_ontology`** - Retrieve terms from a specific ontology ### Direct Python Usage ```python from ols_mcp.tools import search_all_ontologies, get_ontology_info, get_terms_from_ontology # Search for biological terms results = search_all_ontologies("apoptosis", max_results=5) # Get information about Gene Ontology go_info = get_ontology_info("go") # Get terms from a specific ontology terms = get_terms_from_ontology("go", max_results=10) ``` ### CLI Usage #### Running the MCP Server Run the MCP server directly: ```bash ols-mcp ``` #### Testing Individual Tools You can test the tools directly using Python: ```bash # Search for biological terms across all ontologies uv run …