@pipeworx/cdc

Connect: https://gateway.pipeworx.io/cdc/mcp · Install: one-click buttons

Tools: 2

The CDC’s data products: disease surveillance (notifiable conditions, FluView), vital statistics (births, deaths), behavioral risk factors (BRFSS), environmental health, social determinants of health. The authoritative US public-health data. Free, no auth (some datasets require a free token for higher volume).

Why this matters for AI agents

For US public-health questions — disease incidence, mortality rates, behavioral risk factors, environmental exposures — CDC is canonical. Government-grade methodology, transparent data documentation. Pair with WHO Global Health Observatory for international comparisons.

Common flows:

  • Notifiable diseases. Weekly counts by state, condition (TB, salmonella, measles, etc.).
  • Mortality stats. Death counts by cause, demographic, geography. NVSS data going back decades.
  • BRFSS. Behavioral Risk Factor Surveillance System — state-level prevalence of smoking, obesity, diabetes, mental health, etc.
  • Flu / respiratory virus surveillance. Weekly FluView, plus COVID-era respiratory illness reporting.

Auth

Most CDC datasets are open via Socrata’s data.cdc.gov platform; free, lightly rate-limited. For sustained volume, get a free Socrata app token. Pass via _apiKey.

Datasets worth knowing

DatasetCadenceUse
NVSS MortalityAnnual / monthlyDeath counts and rates by cause/age/sex/race/state
FluViewWeeklyFlu activity surveillance
NNDSS (National Notifiable Disease Surveillance)WeeklyReportable diseases by state
BRFSSAnnualState-level risk-factor prevalence
YRBSS (Youth Risk Behavior)BiennialAdolescent health behaviors
NHANESContinuousExamination + lab data, smaller representative sample

For “what’s the rate of X in state Y?” most answers come from NVSS (mortality) or BRFSS (risk factors).

Common pitfalls

  • Suppression for small counts. CDC suppresses cells with <10 deaths or low denominators to protect privacy. The dataset returns null/asterisk; don’t treat as zero.
  • Crude vs age-adjusted rates. Mortality rates per 100k are usually reported as both. Age-adjusted are comparable across populations with different age structures; crude aren’t.
  • Race/ethnicity handling. CDC race categories shifted post-2003 (multi-race added). Time-series across the break needs care.
  • State of residence vs occurrence. Mortality data reports both. Most analyses want residence (where the person lived); some want occurrence (where the death certificate was filed). Read the metadata.
  • Pandemic-era anomalies. 2020-2022 mortality data has classification issues (COVID coding, excess-mortality interpretation). Long-term trends should annotate the disruption.
  • Real-time CDC data is delayed. Weekly FluView ~1-2 week lag. Monthly notifiable diseases ~1 month. NVSS mortality ~6-12 month lag. Plan agent flows accordingly.

Tools

  • search_datasets — Search CDC public health datasets by keyword. Returns dataset names, descriptions, IDs, and update dates. Example: search_datasets(“influenza surveillance”).
  • get_dataset — Get rows from a specific CDC dataset by its Socrata dataset ID (four-by-four format like “xxxx-xxxx”). Returns data rows with all columns. Use search_datasets first to find the ID.

Tools

  • get_dataset — Get rows from a specific CDC dataset by its Socrata dataset ID (four-by-four format like xxxx-xxxx ). Returns data rows with all columns. Use search_datasets first to find the ID.
  • search_datasets — Search CDC public health datasets by keyword. Returns dataset names, descriptions, IDs, and update dates. Example: search_datasets( influenza surveillance ).

Regenerated from source · build May 9, 2026