CDC PLACES MCP Server

⚠️ DISCLAIMER: This is a proof of concept and is not intended for production use. The developers bear no responsibility for the accuracy of the data returned from the tool.

A Model Context Protocol (MCP) server that provides programmatic access to the CDC PLACES dataset for health statistics and outcomes data across US geographic areas.

Overview

The CDC PLACES dataset provides model-based estimates for chronic disease risk factors, health outcomes, and clinical preventive service use for all 50 states, the District of Columbia, and 500 of the largest US cities and census places. This MCP server enables easy access to this comprehensive health data through MCP clients (such as Claude Desktop, Zed, or any MCP-compatible application).

Latest Data: Supports PLACES Release 2025 (using 2023 BRFSS data for most measures)

Features

Available Tools

1. get_cdc_places_data

Fetch health data for specific measures, locations, and time periods.

Parameters:

• year (string): Year of the data release (e.g., "2023", "2022")
• measureid (enum): Health measure identifier (e.g., "CSMOKING", "DIABETES", "OBESITY")
• geo (literal): Geographic level - "state", "county", "census", "zcta", or "places"
• datavaluetypeid (literal): "CrdPrv" (crude prevalence) or "AgeAdjPrv" (age-adjusted prevalence)
• locationname (optional): Location name (e.g., "Wayne" for Wayne County)

Example Query:

Get smoking rates for Wayne County, Michigan in 2023

2. area_summary_stats

Calculate summary statistics across multiple geographic areas within a scope.

Parameters:

• geo_scope (literal): "counties_in_state", "tracts_in_county", or "places_in_state"
• state_code (string): Two-letter state abbreviation (e.g., "CA", "MI")
• year (string): Year of the data release
• measureid (enum): Health measure identifier
• datavaluetypeid (literal): Data value type
• county (optional): County name (required for "tracts_in_county" scope)

Returns: Count, mean, min, Q1, median, Q3, max with location attribution for point statistics

Example Query:

Get obesity statistics across all counties in California for 2023

Supported Health Measures (45 total)

The server supports 45 health measures across 6 categories:

• Health Outcomes (13 measures): ARTHRITIS, BPHIGH, CANCER, CASTHMA, CHD, COPD, DEPRESSION, DIABETES, HIGHCHOL, KIDNEY, OBESITY, STROKE, TEETHLOST
• Health Risk Behaviors (4 measures): BINGE, CSMOKING, LPA, SLEEP
• Health Status (3 measures): GHLTH, MHLTH, PHLTH
• Prevention (10 measures): ACCESS2, BPMED, CERVICAL, CHECKUP, CHOLSCREEN, COLON_SCREEN, COREM, COREW, DENTAL, MAMMOUSE
• Disability (8 measures): HEARING, VISION, COGNITION, MOBILITY, SELFCARE, INDEPLIVE, DISABILITY
• Health-Related Social Needs (7 measures): ISOLATION, FOODSTAMP, FOODINSECU, HOUSINSECU, SHUTUTILITY, LACKTRPT, EMOTIONSPT, LONELINESS

New in 2025: The LONELINESS measure was added to track social isolation indicators.

Installation

Prerequisites

• Python 3.13+
• MCP-compatible client (e.g., Claude Desktop, Zed)

Setup

1. Clone the repository:

git clone https://github.com/GSA-TTS/cdc-places-mcp-server.git
cd cdc-places-mcp-server

2. Install dependencies:

pip install -r requirements.txt

Or using uv:

uv pip install -r requirements.txt

3. Configure your MCP client to use this server (see Configuration section below)

Configuration

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "places": {
      "command": "python",
      "args": ["-m", "places.app"],
      "cwd": "/path/to/cdc-places-mcp-server",
      "env": {
        "PYTHONPATH": "/path/to/cdc-places-mcp-server/src"
      }
    }
  }
}

Zed Editor

Add to Zed settings:

{
  "context_servers": {
    "places": {
      "command": {
        "path": "python",


... [View full README on GitHub](https://github.com/GSA-TTS/cdc-places-mcp-server#readme)