@pipeworx/cdc

Connect: https://pipeworx.io/mcp — every tool in the catalog, including @pipeworx/cdc’s. Install: one-click buttons

No MCP client? Skip the connection: POST https://gateway.pipeworx.io/v1/tools/search_packs {"query":"..."} to find a tool below, GET /v1/tools/<name> for its schema, POST the same URL with arguments for the data — see For AI agents.

Tools: 4

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.
• Wastewater surveillance (NWSS). Weekly national or state SARS-CoV-2/flu/RSV viral activity level from sewershed sampling — the leading indicator ahead of case/hospitalization data, and the only way to answer “what’s the current trend in wastewater levels?” wastewater_national_trend / wastewater_state_trend do this directly; don’t route this question to search_datasets, whose full-text search on “wastewater”/“nwss” returns unrelated pollen/filovirus datasets instead.

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

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

NWSS wastewater viral activity level

wastewater_national_trend and wastewater_state_trend read atcp-73re (“CDC Wastewater Viral Activity Level for SARS-CoV-2, Influenza A and RSV”), published weekly on Fridays from ~800+ sewershed sites. It’s site-level (one row per site per pathogen per week, each with a 5-level category — Very Low/Low/Moderate/High/Very High), so there is no ready-made national or state figure: both tools compute a population-weighted mean of the category rank (1..5) across every reporting site for the grain requested, plus a week-over-week trend (rising/declining/stable, ±0.15 threshold on the weighted score). pathogen accepts loose aliases (covid, flu, rsv); state accepts postal abbreviations (CA) as well as full names.

CDC previously published two “NWSS Public …” datasets (g653-rqe2, 2ew6-ywp6) with a national percentile metric; both stopped updating in Aug 2026 and are now dead ends — CDC replaced them with the per-pathogen raw qPCR datasets (j9g8-acpt SARS-CoV-2, ymmh-divb Influenza A, 45cq-cw4i RSV) and the classified atcp-73re these tools use. Verify before assuming otherwise: curl 'https://data.cdc.gov/resource/atcp-73re.json?$select=max(week_end)'.

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 — Fetch up to 1000 rows from a CDC Socrata dataset by its four-by-four dataset ID (e.g., “9mfq-cb36”). Returns row array with all columns plus column names extracted from the first row. Use search_datas
• wastewater_national_trend — National CDC NWSS wastewater viral activity level (WVAL) for SARS-CoV-2, influenza A, or RSV — the leading public signal for near-term respiratory infection and test-demand trends, published weekly (F
• wastewater_state_trend — CDC NWSS wastewater viral activity level (WVAL) for one US state or territory — same population-weighted national methodology as wastewater_national_trend, scoped to reporting sites within the state.