Track MCP LogoTrack MCP
Track MCP LogoTrack MCP

The world's largest repository of Model Context Protocol servers. Discover, explore, and submit MCP tools.

Product

  • Categories
  • Top MCP
  • New & Updated

Company

  • About

Legal

  • Privacy Policy
  • Terms of Service
  • Cookie Policy

© 2025 TrackMCP. All rights reserved.

Built with ❤️ by Krishna Goyal

    Omop Mcp

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

    14 stars
    Python
    Updated Oct 17, 2025
    ai-agents
    healthcare
    mcp-server
    ohdsi
    omop-cdm

    Documentation

    OMOP MCP Server

    License

    arXiv

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

    Installation

    Before configuring the MCP server, ensure you have:

    1. uv installed on your system

    • Install from: https://docs.astral.sh/uv/getting-started/installation/

    2. Clone the repository

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

    3. Set up environment variables (only for API calls)

    Copy .env.template and configure your API credentials:

    bash
    cp .env.template .env

    Edit .env with API credentials:

    bash
    # Azure OpenAI Configuration
       AZURE_OPENAI_ENDPOINT=
       AZURE_OPENAI_API_KEY=
       AZURE_API_VERSION=
       MODEL_NAME=
    
       # OpenAI Configuration (alternative)
       OPENAI_API_KEY=

    Configuration for Claude Desktop

    Add the following configuration to your claude_desktop_config.json file:

    Location:

    • MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
    • Windows: %APPDATA%/Claude/claude_desktop_config.json

    Configuration:

    Replace `` with the actual path to your cloned repository.

    json
    {
      "mcpServers": {
        "omop_mcp": {
          "command": "uv",
          "args": ["--directory", "", "run", "omop_mcp"]
        }
      }
    }

    Features

    The OMOP MCP server provides the find_omop_concept tool for:

    • Mapping clinical terminology to OMOP concepts
    • Validating terminology mappings
    • Searching OMOP vocabulary
    • Converting between different clinical coding systems

    Usage Example

    • It is recommended to specify the OMOP field and table name in the prompt for improved accuracy.

    Refer to omop_concept_id_fields.json for the list of OMOP fields and tables that store concept IDs.

    • You can specify preferred vocabularies for the mapping in order of priority (e.g., "SNOMED preferred" or "LOINC > SNOMED > RxNorm").

    Prompt:

    code
    Map `Temperature Temporal Scanner - RR` for `measurement_concept_id`
    in the `measurement` table.

    Response:

    code
    CONCEPT_ID: 46235152
    CODE: 75539-7
    NAME: Body temperature - Temporal artery
    CLASS: Clinical Observation
    CONCEPT: Standard
    VALIDITY: Valid
    DOMAIN: Measurement
    VOCAB: LOINC
    URL: https://athena.ohdsi.org/search-terms/terms/46235152
    REASON: This LOINC concept specifically represents body temperature measured
    at the temporal artery, which is what a temporal scanner measures.
    The "RR" in your source term likely refers to "Recovery Room" or
    another location/department indicator, but in OMOP, the location would
    typically be captured in a separate field rather than
    as part of the measurement concept itself.

    Contributing

    See CONTRIBUTING.md for guidelines to contribute to the project.

    Citation Policy

    If you use this software, please cite the pre-print at arXiv (cs.AI) below:

    An Agentic Model Context Protocol Framework for Medical Concept Standardization

    License

    This project is licensed under the Apache License 2.0. See LICENSE file for details.

    Contact: jaerongahn@gmail.com

    Similar MCP

    Based on tags & features

    • FH

      Fhir Mcp Server

      Python·
      55
    • BI

      Biothings Mcp

      Python·
      25
    • PY

      Python Openstackmcp Server

      Python·
      14
    • KI

      Kill Process Mcp

      Python·
      9

    Trending MCP

    Most active this week

    • PL

      Playwright Mcp

      TypeScript·
      22.1k
    • SE

      Serena

      Python·
      14.5k
    • MC

      Mcp Playwright

      TypeScript·
      4.9k
    • MC

      Mcp Server Cloudflare

      TypeScript·
      3.0k
    View All MCP Servers

    Similar MCP

    Based on tags & features

    • FH

      Fhir Mcp Server

      Python·
      55
    • BI

      Biothings Mcp

      Python·
      25
    • PY

      Python Openstackmcp Server

      Python·
      14
    • KI

      Kill Process Mcp

      Python·
      9

    Trending MCP

    Most active this week

    • PL

      Playwright Mcp

      TypeScript·
      22.1k
    • SE

      Serena

      Python·
      14.5k
    • MC

      Mcp Playwright

      TypeScript·
      4.9k
    • MC

      Mcp Server Cloudflare

      TypeScript·
      3.0k