UCSFOMOPAgent

BaranziniLab/UCSFOMOPAgent
★ 0 stars Python Database Updated today
MCP server for UCSF OMOP clinical database
View on GitHub → Try with Claude — $10 free →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "ucsfomopagent": {
      "command": "uvx",
      "args": [
        "ucsfomopagent"
      ]
    }
  }
}

Or install with pip: pip install ucsfomopagent

README Excerpt

An MCP (Model Context Protocol) server for querying the **UCSF OMOP** de-identified electronic health records database (OMOP CDM v5.4 on Microsoft SQL Server) for fast, robust clinical data retrieval. > **v0.2.0** is a major upgrade focused on getting the LLM to the *right* data > *faster* and *more reliably*, while staying robust to database changes. See

Tools (14)

CLINICAL_RECORDS_DATABASECLINICAL_RECORDS_PASSWORDCLINICAL_RECORDS_SERVERCLINICAL_RECORDS_USERNAMEINFOOMOP_DEIDOMOP_LOG_LEVELOMOP_SCHEMAfind_measurementget_omop_schemalist_ucsf_omop_tablesomopquery_ucsf_omopsearch_concepts
📊
Working with market or time-series data?
The Polymarket Historical Dataset — 18.5M+ price snapshots across 18,600+ prediction markets (CSV + SQLite). Built for backtesting & ML.
View dataset →