Enterprise DNA
M MCP Servers Developer low

OHNLP/omop_mcp

by Various

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

O

MCP

OHNLP/omop_mcp

Added 1 June 2026

#ai-agents #healthcare #mcp-server #ohdsi #omop-cdm

Overview

OHNLP/omop_mcp is a Model Context Protocol server that maps clinical terminology to Observational Medical Outcomes Partnership (OMOP) concepts using large language models. It provides a standardized interface for tools to query an LLM for concept mapping.

Best for

Best for
Developers integrating clinical terminology mapping into healthcare software using large language models

Use cases

  • Integrating clinical NLP into healthcare applications
  • Mapping free-text clinical notes to standardized OMOP codes
  • Building a decision support tool that uses OMOP concept mapping

Notes

OHNLP/omop_mcp is a Model Context Protocol server that maps clinical terminology to Observational Medical Outcomes Partnership (OMOP) concepts using large language models. It provides a standardized interface for tools to query an LLM for concept mapping.

35 stars on GitHub. Last updated 2026-05-11.

Use cases

  • Integrating clinical NLP into healthcare applications
  • Mapping free-text clinical notes to standardized OMOP codes
  • Building a decision support tool that uses OMOP concept mapping

Pros

  • Uses a standardized protocol (MCP) for tool integration
  • Leverages LLMs for flexible mapping of varied clinical terms
  • Open source and written in Python, easy to extend

Cons

  • Requires running an LLM, which may be computationally expensive
  • Mapping accuracy depends on the quality and training of the LLM
  • Small community (35 stars) means limited support and documentation

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • Uses a standardized protocol (MCP) for tool integration
  • Leverages LLMs for flexible mapping of varied clinical terms
  • Open source and written in Python, easy to extend

Cons

  • Requires running an LLM, which may be computationally expensive
  • Mapping accuracy depends on the quality and training of the LLM
  • Small community (35 stars) means limited support and documentation