OMOPSAFE
Model Context Protocol (MCP) server for mapping clinical terminology to Observational Medical Outcomes Partnership (OMOP) concepts using Large Language Models
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://arxiv.org/abs/2509.03828)
Model Context Protocol (MCP) server for mapping clinical terminology to Observational Medical Outcomes Partnership (OMOP) concepts using Large Language Models (LLMs). The vocabulary API is supported by OMOP HUB, and you can obtain an API key from omophub.com.
Demo Website
Overview
This server provides an agentic framework to standardize medical terms into the OMOP Common Data Model (CDM). It uses the OMOPHub API for vocabulary searching, concept suggestion, and terminology mapping.
Installation
Before configuring the MCP server, ensure you have:
- uv installed on your system
- Install from: https://docs.astral.sh/uv/getting-started/installation/
- Clone the repository
git clone https://github.com/OHNLP/omop_mcp.git cd omop_mcp
- Set up environment variables
Copy .env.template to .env and fill in your API credentials. You will need both an LLM provider key and an [OMOPHUB_API_KEY](https://omophub.com) (for vocabulary lookups).
cp .env.template .env
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.
{
"mcpServers": {
"omop_mcp": {
"command": "uv",
"args": ["--directory", "", "run", "omop_mcp"]
}
}
}Features
The OMOP MCP server provides tools and resources for:
- Mapping clinical terminology: Intelligent mapping of free-tex
17769122b41fOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add omop_mcp --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env AZURE_OPENAI_API_KEY=${AZURE_OPENAI_API_KEY} --env GOOGLE_API_KEY=${GOOGLE_API_KEY} --env GROQ_API_KEY=${GROQ_API_KEY} -- uvx omop_mcp{
"mcpServers": {
"omop_mcp": {
"command": "uvx",
"args": [
"omop_mcp"
],
"env": {
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"AZURE_OPENAI_API_KEY": "${AZURE_OPENAI_API_KEY}",
"GOOGLE_API_KEY": "${GOOGLE_API_KEY}",
"GROQ_API_KEY": "${GROQ_API_KEY}"
}
}
}
}Exposed tools (2)
2 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
batch_map_concepts_from_csv | read | |
find_omop_concept | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (5)
performance_evaluation.xlsx
.env.template
.pre-commit-config.yaml
config_path = os.path.join(config_dir, "../../omop_mcp_config.json")
sudo find . -name git-cliff -type f -executable -exec sudo mv {} /usr/local/bin/ \;Gates applied: no_behavioural_pass.
17769122b41ffull audit observations/trust-audit/mcp-server/ohnlp__omop.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 17769122b41f | SAFE | B | 89 | first audit |
Questions
What is the OMOP MCP server?
Model Context Protocol (MCP) server for mapping clinical terminology to Observational Medical Outcomes Partnership (OMOP) concepts using Large Language Models
What tools does OMOP expose?
2 in total: 2 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is OMOP safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does OMOP need?
It reads ANTHROPIC_API_KEY, AZURE_OPENAI_API_KEY, GOOGLE_API_KEY, GROQ_API_KEY, HUGGINGFACEHUB_API_TOKEN, OMOPHUB_API_KEY, OPENAI_API_KEY and OPENROUTER_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (17769122b41f), read on 2026-10-08. The repository is watched and re-audited when it changes.