Public Hosted Server: https://cdc.caseyjhand.com/mcp

Tools

Four tools for discovering and querying CDC public health data. Three query the CDC Open Data portal (Socrata); one queries CDC WONDER mortality statistics:

| Tool | Description | |:---|:---| | cdc_discover_datasets | Search the catalog by keyword, category, or tag. Entry point for all queries. | | cdc_get_dataset_schema | Fetch column schema, row count, and metadata for a dataset. Essential before writing SoQL queries. | | cdc_query_dataset | Execute SoQL queries — filter, aggregate, sort, full-text search, and field selection. | | cdc_query_wonder | Query CDC WONDER for national mortality statistics (deaths, population, crude/age-adjusted rates) by year, age, sex, and race, filtered by ICD-10 cause. |

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, truncated descriptions, a column count with a short column sample, and update timestamps — use cdc_get_dataset_schema for the full column list
• Pagination via offset for browsing large result sets
• domain selects the portal: data.cdc.gov (default) or chronicdata.cdc.gov

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)
• domain selects the portal hosting the dataset: data.cdc.gov (default) or chronicdata.cdc.gov

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
• domain selects the portal hosting the dataset: data.cdc.gov (default) or chronicdata.cdc.gov

cdc_query_wonder

Query CDC WONDER for national US mortality statistics from the Underlying Cause of Death database (D76, 1999–2020) — a separate CDC system from the Socrata datasets the other tools query.

• Group results by any of year, age_group, sex, race (1–4 dimensions)
• Filter by ICD-10 underlying cause, sex, ten-year age groups, and year range
• Returns deaths, population, and crude death rate, plus age-adjusted rate when not grouping by age
• National totals only — sub-national (state/county) breakdowns are not available through the WONDER API (CDC vital-statistics policy)
• CDC suppresses any cell with fewer than 10 deaths (returned as null)
• Rate-limited to one request per ~15 seconds; requests are spaced automatically

Resources and prompt

| Type | Name | Description | |:---|:---|:---| | Resource | cdc://datasets | Top 50 datasets by popularity for orientation | | Resource | cdc://datasets/{datasetId} | Dataset metadata and column schema (equivalent to schema tool) | | Prompt | analyze_health_trend | Guided 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
• Adds CDC WONDER mortality access (cdc_query_wonder) — national deaths, population, and crude/age-adjusted rates from the Underlying Cause of Death database (1999–2020), a separate XML-over-HTTP CDC system
• Discovery-first approach for a heterogeneous catalog (~1,487 datasets across many health domains)
• Two CDC Socrata portals via the domain input — data.cdc.gov (default) and chronicdata.cdc.gov (PLACES small-area estimates, the Heart Disease & Stroke Atlas, Environmental Public Health Tracking); restricted to this allowlist
• 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

Public Hosted Instance

A public instance is available at https://cdc.caseyjhand.com/mcp — no installation required. Point any MCP client at it via Streamable HTTP:

{
  "mcpServers": {
    "cdc-health-mcp-server": {
      "type": "streamable-http",
      "url": "https://cdc.caseyjhand.com/mcp"
    }
  }
}

Self-Hosted / Local

Add the following to your MCP client configuration file.

{
  "mcpServers": {
    "cdc-health-mcp-server": {
      "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-mcp-server": {
      "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-mcp-server": {
      "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

• Bun v1.3.2 or higher.
• Optional: Socrata app token for higher rate limits.

Installation

1. Clone the repository:

git clone https://github.com/cyanheads/cdc-health-mcp-server.git

2. Navigate into the directory:

cd cdc-health-mcp-server

3. Install dependencies:

bun install

Configuration

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

| Variable | Description | Default | |:---|:---|:---| | MCP_TRANSPORT_TYPE | Transport: stdio or http | stdio | | MCP_HTTP_PORT | HTTP server port | 3010 | | MCP_AUTH_MODE | Authentication: none, jwt, or oauth | none | | MCP_LOG_LEVEL | Log level (debug, info, warning, error, etc.) | info | | LOGS_DIR | Directory for log files (Node.js only) | <project-root>/logs | | STORAGE_PROVIDER_TYPE | Storage backend: in-memory, filesystem, supabase, cloudflare-kv/r2/d1 | in-memory | | CDC_APP_TOKEN | Socrata app token for higher rate limits | none | | CDC_BASE_URL | Base URL for SODA API requests | https://data.cdc.gov | | CDC_CATALOG_URL | Base URL for Socrata Discovery API | https://api.us.socrata.com/api/catalog/v1 | | OTEL_ENABLED | Enable OpenTelemetry instrumentation (spans, metrics, completion logs) | false |

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

| Directory | Purpose | |:---|:---| | src/mcp-server/tools | Tool definitions (*.tool.ts). Three CDC data tools. | | src/mcp-server/resources | Resource definitions. Catalog overview and dataset detail. | | src/mcp-server/prompts | Prompt definitions. Health trend analysis workflow. | | src/services/socrata | Socrata SODA API service layer — HTTP client, catalog search, metadata, queries. | | src/config | Server-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.