Omop MCP Server

Map clinical terminology to standardized OMOP common data model concepts via LLMs.

Data last scanned today · Reviewed today

301 tool39PythonNOASSERTION

Overview

The OMOP MCP server facilitates the transformation of unstructured medical text into standardized terminology by leveraging the OMOP Common Data Model. By connecting to the OMOPHub API, it enables users to perform intelligent mapping of clinical terms, search medical vocabularies, and automate the identification of standardized concepts like LOINC and SNOMED codes. Users can process individual terms or handle batch requests directly from CSV files to streamline medical data standardization. To operate the server, users must provide their own OMOPHub API credentials alongside their chosen LLM provider key. The implementation relies on the uv package manager and requires manual cloning of the repository to local infrastructure, after which it can be configured for integration with various AI environments.

Our verdict

This server is assigned a high-risk security score of 30/100. The primary security concern is the lack of a read-only mode, meaning every installation grants full write access by default, which may be inappropriate for sensitive clinical data environments. Furthermore, the project lacks official vendor maintenance and community authentication review, making it best suited for experimental research or local development rather than sensitive healthcare deployments.

  • Supports automated batch mapping of clinical concepts from CSVs
  • Provides domain-specific vocabulary prioritization for LOINC and SNOMED
  • Contains zero direct dependencies to minimize supply-chain surface area
  • Includes documented support for OMOP Common Data Model integration
  • Operates with full write access without a read-only configuration
  • Lacks authentication security reviews for API credential handling
  • Maintained by a single contributor with no official vendor backing
  • License status is marked as NOASSERTION

Tools

ToolDescriptionRisk
find_omop_conceptDirect access to OMOP vocabulary.low

Compatibility

ClientLocalDockerRemoteRead-only
Claude Desktop
Cursor
VS Code
Windsurf
ChatGPT

Frequently asked questions

What API credentials are required to run the server?

You must provide an API key for your LLM provider and an OMOPHUB_API_KEY obtained from omophub.com.

What are the system requirements for installing the server?

You must have uv installed on your system and the repository cloned to your local machine.

How is the server configured for use with Claude Desktop?

You need to add an entry to your claude_desktop_config.json file that points to your local repository directory and runs the server via uv.

Does the server support mapping more than one clinical term at a time?

Yes, the server includes a tool specifically designed for batch processing of concepts from a CSV file.

Is it necessary to provide context when using the mapping tools?

While not strictly required, the agent is most effective when provided with specific context, such as the target OMOP table or field name.

Badge

Omop MCP Server security score, rated on RepoAI

Maintain this server? Add the live badge to your README.