ICF MCP Server
Enables lookup, search, browsing, and explanation of WHO's International Classification of Functioning, Disability and Health (ICF) codes and qualifiers via the WHO ICD-API.
README
ICF MCP Server
A Model Context Protocol (MCP) server that provides access to the WHO International Classification of Functioning, Disability and Health (ICF) via the WHO ICD-API.
What is ICF?
The ICF is a WHO classification that complements ICD (diagnosis codes) by describing how health conditions affect a person's functioning in daily life. It covers:
- Body Functions (b) - Physiological and psychological functions
- Body Structures (s) - Anatomical parts of the body
- Activities and Participation (d) - Task execution and life involvement
- Environmental Factors (e) - Physical, social, and attitudinal environment
Tools
| Tool | Description |
|---|---|
icf_lookup |
Look up a specific ICF code (e.g., b280, d450) |
icf_search |
Search by keyword (e.g., "walking difficulty", "pain") |
icf_browse_category |
Browse top-level categories: b, s, d, e |
icf_get_children |
Get subcategories of a code |
icf_explain_qualifier |
Explain severity ratings (0-4, 8, 9) |
icf_overview |
Full ICF classification overview |
Prerequisites
- WHO ICD-API credentials (free): Register at https://icd.who.int/icdapi
- Python 3.11+
Installation
# Clone the repository
git clone https://github.com/stayce/icf-mcp-server.git
cd icf-mcp-server
# Create virtual environment
python3 -m venv .venv
source .venv/bin/activate
# Install dependencies
pip install -e .
Configuration
Create a .env file with your WHO API credentials:
cp .env.example .env
# Edit .env with your credentials
Usage with Claude Desktop
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"icf": {
"command": "/path/to/icf-mcp-server/.venv/bin/python",
"args": ["-m", "icf_mcp"],
"env": {
"WHO_ICD_CLIENT_ID": "your_client_id",
"WHO_ICD_CLIENT_SECRET": "your_client_secret"
}
}
}
}
Restart Claude Desktop to load the server.
Example Queries
Once configured, you can ask Claude:
- "Look up ICF code b280"
- "Search ICF for walking difficulties"
- "What are the subcategories under d4 (Mobility)?"
- "Explain ICF qualifier 3"
- "Give me an overview of the ICF classification"
Development
# Install in development mode
pip install -e .
# Run tests
python -m pytest
# Test the client directly
python -c "
import asyncio
from icf_mcp.who_client import WHOICFClient
async def test():
client = WHOICFClient(client_id='...', client_secret='...')
results = await client.search('pain')
print(results)
await client.close()
asyncio.run(test())
"
API Reference
This server uses the WHO ICD-API which provides programmatic access to both ICD-11 and ICF classifications.
- API Documentation: https://icd.who.int/docs/icd-api/APIDoc-Version2/
- ICF Browser: https://icd.who.int/dev11/l-icf/en
License
MIT License - see LICENSE
Contributing
Contributions welcome! Please open an issue or submit a pull request.
Acknowledgments
- World Health Organization for the ICD-API
- Anthropic for the Model Context Protocol
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.