MCPgee
MCPgee
MCPgeeMCPgee

OMOP MCP

v1.0.0•Data Science & ML•stable

Model Context Protocol (MCP) server for mapping clinical terminology to Observational Medical Outcomes Partnership (OMOP) concepts using Large Language Models

ai-agentshealthcaremcp-serverohdsiomop-cdm
Share:
35
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is OMOP MCP?

OMOP MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol (mcp) server for mapping clinical terminology to observational medical outcomes partnership (omop) concepts using large language models

Model Context Protocol (MCP) server for mapping clinical terminology to Observational Medical Outcomes Partnership (OMOP) concepts using Large Language Models

This server falls under the Data Science & ML and Databases categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Model Context Protocol (MCP) server for mapping clinical ter

Use Cases

Map clinical terminology to OMOP standard concepts.
Process healthcare data in standardized format.
Enable AI analysis of clinical datasets.
OHNLP

Maintainer

LicenseNOASSERTION
Languagepython
Versionv1.0.0
UpdatedMay 19, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx omop

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use OMOP MCP

The OMOP MCP Server bridges clinical free-text and structured healthcare data by mapping natural language terminology to OMOP (Observational Medical Outcomes Partnership) standard concepts using large language models. It connects to the OMOPHub vocabulary API to resolve clinical terms — such as lab test names, diagnoses, or medications — into canonical concept IDs, domains, vocabulary sources, and validity status. Researchers and data engineers working with OHDSI cohort definitions or clinical data pipelines can use it to standardize terminology without manual vocabulary lookups.

Prerequisites

  • Python 3.10 or later installed
  • uv package manager installed
  • An OMOPHUB_API_KEY from omophub.com (free registration required)
  • An MCP client such as Claude Desktop
1

Clone the repository

Clone the OMOP MCP server repository from the OHNLP GitHub organization.

git clone https://github.com/OHNLP/omop_mcp.git
cd omop_mcp
2

Obtain an OMOPHub API key

Register at omophub.com to get your free OMOPHUB_API_KEY. This key is required for vocabulary lookups against the OMOP concept database.

3

Install dependencies

Install the project dependencies using uv. uv will automatically manage the virtual environment.

uv sync
4

Add the server to your MCP client config

Add the omop_mcp entry to your Claude Desktop claude_desktop_config.json, providing the repo path and your API key.

{
  "mcpServers": {
    "omop_mcp": {
      "command": "uv",
      "args": ["--directory", "/path/to/omop_mcp", "run", "omop_mcp"],
      "env": {
        "OMOPHUB_API_KEY": "your_omophub_api_key_here"
      }
    }
  }
}
5

Restart Claude Desktop and test a mapping

Restart Claude Desktop, then ask it to map a clinical term to an OMOP concept to verify the server is working correctly.

OMOP MCP Examples

Client configuration

Claude Desktop JSON config for the OMOP MCP server with the required API key.

{
  "mcpServers": {
    "omop_mcp": {
      "command": "uv",
      "args": ["--directory", "/Users/yourname/omop_mcp", "run", "omop_mcp"],
      "env": {
        "OMOPHUB_API_KEY": "your_omophub_api_key_here"
      }
    }
  }
}

Prompts to try

Example prompts for clinical terminology mapping and OMOP concept lookup.

- "Map 'Temperature Temporal Scanner' to an OMOP measurement concept and give me the concept ID"
- "What is the OMOP standard concept for 'type 2 diabetes mellitus'?"
- "Find the LOINC code for serum creatinine in the OMOP vocabulary"
- "Map these lab test names to OMOP concepts: HbA1c, eGFR, TSH"
- "What domain does the concept 'metformin' belong to in OMOP?"

Troubleshooting OMOP MCP

API key error or vocabulary lookup returns no results

Verify your OMOPHUB_API_KEY is set correctly in the env section and that it was obtained from omophub.com. Test the key by visiting the OMOPHub API documentation page.

uv command not found or dependency installation fails

Install uv by running: curl -LsSf https://astral.sh/uv/install.sh | sh — then reopen your terminal and retry uv sync from the omop_mcp directory.

Concept mapping returns low-confidence or incorrect results

Provide more specific clinical terminology in your prompt, including the measurement domain context (e.g., 'as a measurement_concept_id') to help the LLM select the correct vocabulary domain and prioritize LOINC, SNOMED, or RxNorm appropriately.

Frequently Asked Questions about OMOP MCP

What is OMOP MCP?

OMOP MCP is a Model Context Protocol (MCP) server that model context protocol (mcp) server for mapping clinical terminology to observational medical outcomes partnership (omop) concepts using large language models It connects AI assistants to external tools and data sources through a standardized interface.

How do I install OMOP MCP?

Follow the installation instructions on the OMOP MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with OMOP MCP?

OMOP MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is OMOP MCP free to use?

Yes, OMOP MCP is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

OMOP MCP Alternatives — Similar Data Science & ML Servers

Looking for alternatives to OMOP MCP? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.

Ultrarag

★ 5.6k

A 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

★ 2.1k

Aix-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

★ 1.7k

Open 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

★ 1.5k

Bridges 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.

Data Science & MLDatabasesBrowse All Servers

Quick Config Preview

{ "mcpServers": { "omop": { "command": "npx", "args": ["-y", "omop"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use OMOP MCP?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides