MCP Hub
Back to servers

cdc-health-mcp-server

MCP server for discovering and querying CDC public health datasets via the Socrata SODA API.

Registry
Updated
Apr 3, 2026

Quick Install

npx -y @cyanheads/cdc-health-mcp-server

@cyanheads/cdc-health-mcp-server

MCP server for the CDC Open Data portal. Search ~1,487 public health datasets, inspect schemas, and execute SoQL queries across disease surveillance, mortality, vaccinations, behavioral risk, and more. STDIO or Streamable HTTP.

3 Tools • 2 Resources • 1 Prompt

npm Version Framework MCP SDK

License TypeScript Bun


Tools

Three tools for discovering and querying CDC public health data:

ToolDescription
cdc_discover_datasetsSearch the catalog by keyword, category, or tag. Entry point for all queries.
cdc_get_dataset_schemaFetch column schema, row count, and metadata for a dataset. Essential before writing SoQL queries.
cdc_query_datasetExecute SoQL queries — filter, aggregate, sort, full-text search, and field selection.

cdc_discover_datasets

Search the CDC dataset catalog to find relevant datasets.

  • Full-text search across dataset names and descriptions
  • Filter by domain category (e.g., "NNDSS", "Vaccinations", "Behavioral Risk Factors")
  • Filter by domain tags (e.g., ["covid19", "surveillance"])
  • Returns dataset IDs, names, descriptions, column lists, and update timestamps
  • Pagination via offset for browsing large result sets

cdc_get_dataset_schema

Fetch the full column schema for a specific dataset.

  • Column names, data types, and descriptions
  • Row count and last-updated timestamp
  • Essential for understanding column types before writing $where clauses
  • Accepts four-by-four dataset identifiers (e.g., bi63-dtpu)

cdc_query_dataset

Execute SoQL queries against any CDC dataset.

  • Full SoQL support: $select, $where, $group, $having, $order
  • Full-text search across all text columns via $q
  • Up to 5,000 rows per request with pagination
  • Returns the assembled SoQL query string for debugging
  • All response values are strings (per SODA v2.1) — parse based on column type metadata

Resources and prompt

TypeNameDescription
Resourcecdc://datasetsTop 50 datasets by popularity for orientation
Resourcecdc://datasets/{datasetId}Dataset metadata and column schema (equivalent to schema tool)
Promptanalyze_health_trendGuided 5-step workflow: discover, inspect, baseline query, compare, synthesize

Features

Built on @cyanheads/mcp-ts-core:

  • Declarative tool definitions — single file per tool, framework handles registration and validation
  • Unified error handling across all tools
  • Pluggable auth (none, jwt, oauth)
  • Swappable storage backends: in-memory, filesystem, Supabase, Cloudflare KV/R2/D1
  • Structured logging with optional OpenTelemetry tracing
  • Runs locally (stdio/HTTP) or on Cloudflare Workers from the same codebase

CDC-specific:

  • Wraps the Socrata SODA API v2.1 — no auth required, optional app token for higher rate limits
  • Discovery-first approach for a heterogeneous catalog (~1,487 datasets across many health domains)
  • Conservative request spacing for rate limit compliance (no rate-limit headers returned by Socrata)
  • Handles SODA string-typed responses — all values returned as strings, parsed via column type metadata

Getting started

Add the following to your MCP client configuration file.

{
  "mcpServers": {
    "cdc-health": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/cdc-health-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with npx (no Bun required):

{
  "mcpServers": {
    "cdc-health": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cyanheads/cdc-health-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with Docker:

{
  "mcpServers": {
    "cdc-health": {
      "type": "stdio",
      "command": "docker",
      "args": ["run", "-i", "--rm", "-e", "MCP_TRANSPORT_TYPE=stdio", "ghcr.io/cyanheads/cdc-health-mcp-server:latest"]
    }
  }
}

For Streamable HTTP, set the transport and start the server:

MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http
# Server listens at http://localhost:3010/mcp

Prerequisites

Installation

  1. Clone the repository:
git clone https://github.com/cyanheads/cdc-health-mcp-server.git
  1. Navigate into the directory:
cd cdc-health-mcp-server
  1. Install dependencies:
bun install

Configuration

All configuration is validated at startup via Zod schemas in src/config/server-config.ts. Key environment variables:

VariableDescriptionDefault
MCP_TRANSPORT_TYPETransport: stdio or httpstdio
MCP_HTTP_PORTHTTP server port3010
MCP_AUTH_MODEAuthentication: none, jwt, or oauthnone
MCP_LOG_LEVELLog level (debug, info, warning, error, etc.)info
LOGS_DIRDirectory for log files (Node.js only)<project-root>/logs
STORAGE_PROVIDER_TYPEStorage backend: in-memory, filesystem, supabase, cloudflare-kv/r2/d1in-memory
CDC_APP_TOKENSocrata app token for higher rate limitsnone
CDC_BASE_URLBase URL for SODA API requestshttps://data.cdc.gov
CDC_CATALOG_URLBase URL for Socrata Discovery APIhttps://api.us.socrata.com/api/catalog/v1
OTEL_ENABLEDEnable OpenTelemetryfalse

Running the server

Local development

  • Build and run the production version:

    # One-time build
    bun run rebuild
    
    # Run the built server
    bun run start:http
    # or
    bun run start:stdio
    
  • Run checks and tests:

    bun run devcheck  # Lints, formats, type-checks, and more
    bun run test      # Runs the test suite
    

Project structure

DirectoryPurpose
src/mcp-server/toolsTool definitions (*.tool.ts). Three CDC data tools.
src/mcp-server/resourcesResource definitions. Catalog overview and dataset detail.
src/mcp-server/promptsPrompt definitions. Health trend analysis workflow.
src/services/socrataSocrata SODA API service layer — HTTP client, catalog search, metadata, queries.
src/configServer-specific environment variable parsing and validation with Zod.

Development guide

See CLAUDE.md for development guidelines and architectural rules. The short version:

  • Handlers throw, framework catches — no try/catch in tool logic
  • Use ctx.log for logging, ctx.state for storage
  • Register new tools and resources in the createApp() arrays

Contributing

Issues and pull requests are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

License

This project is licensed under the Apache 2.0 License. See the LICENSE file for details.

Reviews

No reviews yet

Sign in to write a review