> ## Documentation Index
> Fetch the complete documentation index at: https://docs.omophub.com/llms.txt
> Use this file to discover all available pages before exploring further.

# AI agent onboarding for OMOP medical vocabularies

> Give AI agents grounded access to 10M+ OMOP medical concepts with zero hallucination risk - search, map, and navigate vocabularies from any client.

## Why OMOPHub for AI?

LLMs are powerful reasoning engines, but they hallucinate clinical codes. OMOPHub provides the verification layer: a vocabulary API covering SNOMED CT, ICD-10, RxNorm, LOINC, and 100+ medical terminologies.

Your AI agent extracts clinical meaning from text. OMOPHub grounds it in verified OMOP concept IDs. No fabricated codes, no "mostly right" in a setting where mostly right is dangerously wrong.

## Prerequisites

<Steps>
  <Step title="Create an account">
    Sign up at [dashboard.omophub.com](https://dashboard.omophub.com).
  </Step>

  <Step title="Generate an API key">
    Go to **API Keys** in your dashboard and create a new key.
  </Step>
</Steps>

## Choose Your Integration Path

<CardGroup cols={2}>
  <Card title="MCP Server" icon="plug" href="/ai/mcp-server">
    Connect OMOPHub to Claude, Cursor, VS Code, or any MCP-compatible AI client.
    Install in under a minute.
  </Card>

  <Card title="Docs for Agents" icon="file-lines" href="/ai/docs-for-agents">
    Feed your AI agent the right documentation format: `llms.txt`, `llms-full.txt`,
    or `skill.md`.
  </Card>

  <Card title="MCP Tools Reference" icon="wrench" href="/ai/mcp-tools">
    Detailed reference for all 6 MCP tools: parameters, descriptions, and example
    usage.
  </Card>

  <Card title="Integration Guide" icon="link" href="/ai/integration-guide">
    Build grounded clinical AI pipelines with the OMOP-Loop pattern. Eliminate
    hallucinated codes in production.
  </Card>
</CardGroup>

## What You Can Do

| Capability                   | Description                                                              |
| :--------------------------- | :----------------------------------------------------------------------- |
| **Concept lookup**           | Find OMOP concept IDs for any clinical term in seconds                   |
| **Cross-vocabulary mapping** | Map between ICD-10, SNOMED, RxNorm, LOINC, and 100+ vocabularies         |
| **Hierarchy navigation**     | Explore ancestors and descendants for phenotype definitions              |
| **Concept set building**     | Let your AI agent assemble complete concept sets for cohort definitions  |
| **Code validation**          | Verify medical codes and check their standard mappings                   |
| **Hallucination detection**  | Validate every LLM-generated concept ID against the OMOP source of truth |