PopHIVE provides AI agents with access to community-level U.S. public health data, enabling them to explore disease trends, compare health indicators across states and counties, analyze vaccination rates and chronic conditions, and investigate social determinants of health using data from multiple sources.
VS Code
Encrypted at rest, isolated from the model
Resolved from an AES-256-GCM vault at the moment of the call and attached to the request — the model never sees the secrets.
Try asking
Cross-disease situation report for one US state or the nation — what's elevated, rising, declining, or stale across every PopHIVE topic. For straightforward single-slice questions only (e.g. "anything elevated in Connecticut?", "public health sitrep for Florida?"). If the answer needs anything beyond reading one precomputed evidence block, use get_data. Examples: "What's going on health-wise in Texas?", "Public health sitrep for Florida", "Anything elevated in Connecticut?" Not for: a single disease (get_current_status), time series (get_trend), ranking states by one disease (get_map). Call example: get_overview(geography='Texas') Scope: US-only aggregate surveillance; relay the precomputed evidence, never re-derive numbers.
Current-status verdict for one disease in one US place — level, direction, and risk right now. For straightforward single-slice questions only (e.g. "is flu rising in Texas?", "how bad is COVID nationally?"). If the answer needs anything beyond reading one precomputed evidence block, use get_data. Examples: "Is RSV rising in Connecticut?", "How bad is flu nationally?", "What is the risk of measles in Texas?", "Current COVID situation in New York." Not for: trends over time (get_trend), ranking geographies (get_map), vaccination coverage (get_coverage). Call example: get_current_status(disease='rsv', geography='Connecticut') Scope: US-only aggregate surveillance; relay the precomputed evidence, never re-derive numbers.
Trend over time for one disease in one US place — direction, peak, and change, optionally stratified or pinned to one source. For straightforward single-slice questions only (e.g. "how has RSV changed since January?", "flu trend in Ohio"). If the answer needs anything beyond reading one precomputed evidence block, use get_data. Examples: "What are the latest trends in COVID?", "How has flu changed since January?", "Diabetes trend in Ohio over 5 years." season_over_season evidence compares the current season to the immediately prior season only; for older seasons use get_data. Not for: a current-status verdict (get_current_status), ranking geographies (get_map), vaccination coverage (get_coverage). Call example: get_trend(disease='flu', geography='US', period='12w') Scope: US-only aggregate surveillance; relay the precomputed evidence, never re-derive numbers.
Geographic ranking — which US states or counties are highest or lowest on one disease, by current level or recent change. For straightforward single-slice questions only (e.g. "which counties have the highest RSV?", "how does Texas rank on flu?"). If the answer needs anything beyond reading one precomputed evidence block, use get_data. Examples: "What parts of the US have the highest rates of flu right now?", "How do diabetes rates differ across the US by county?", "How does Texas rank?", "Which states are improving fastest on opioid overdose?" Not for: trends over time (get_trend), one place's status (get_current_status). Call example: get_map(disease='flu', geo_level='state', top_n=10) Scope: US-only aggregate surveillance; relay the precomputed evidence, never re-derive numbers.
Side-by-side comparison of one disease across 2–5 US places, or agreement between surveillance sources in one place. For straightforward single-slice questions only (e.g. "is RSV worse in CT than NY?", "do wastewater and ED visits agree on COVID?"). If the answer needs anything beyond reading one precomputed evidence block, use get_data. Examples: "Is RSV worse in CT than NY?", "Compare diabetes in Texas vs California", "Do wastewater and ED visits agree on COVID?" Not for: one place's status (get_current_status), ranking many places (get_map). Call example: compare(disease='covid', geographies=['Texas', 'Florida']) Scope: US-only aggregate surveillance; relay the precomputed evidence, never re-derive numbers.
US childhood vaccination coverage — the rate for one vaccine in one place and whether it meets targets. For straightforward single-slice questions only (e.g. "kindergarten MMR rate in Idaho?", "is Texas below 95% MMR?"). If the answer needs anything beyond reading one precomputed evidence block, use get_data. Examples: "Kindergarten MMR rate in Idaho?", "Is Texas below 95% MMR?", "Polio vaccination rate in Connecticut." Not for: disease activity (get_current_status), trends (get_trend), coverage rankings across states (get_map with disease='mmr'). Call example: get_coverage(vaccine='mmr', geography='Idaho') Scope: US-only aggregate surveillance; relay the precomputed evidence, never re-derive numbers.
Data catalog and raw-data gateway. The six specialized tools answer single-slice questions — current status, trend, map/ranking, A-vs-B compare, coverage — with server-verified evidence; try them first, escalating here costs one call. Use get_data when evidence can't carry the answer: multi-stratum gaps, history beyond the served window, complete lists, cross-dataset joins, custom math. Flow: (1) catalog, (2) disease='about' for the guide, (3) view schema + data_url, (4) download and compute — results are yours but carry the caveats and aren't server-verified. include_query=true returns a runnable pandas snippet. Topics: annual_wellness_visit, antimicrobial_resistance, babesiosis, breast_cancer_screening, campylobacter, cardiovascular_screening, census, cervical_cancer_screening, chlamydia_screening, colorectal_cancer_screening, combined7, community_health, copd, covid19, dengue, depression_screening, diabetes, diabetes_screening, diarrhea, dtap, ehrlichiosis, enteric_disease, firearm_injury, flu_vaccine_adult, haemophilus_influenzae, healthcare_access, heat_illness, hepa, hepb, hib, infant_mortality, influenza, injury_deaths, low_birth_weight, malaria, maternal_health, maternal_mortality, measles, mmr, obesity, opioid_overdose, opioid_use_disorder, pcv, pelvic_exam, pertussis, pneumococcal_vaccine_adult, polio, prostate_cancer_screening, rotavirus, rsv, salmonella, shigella, stec, strep, teen_births, vaccine_exemptions, varicella, vector_borne, west_nile, youth_wellbeing. Examples: "What does PopHIVE track?", "Do you have Lyme disease data?", "Vaccination gaps across insurance types", "Raw RSV data for Connecticut." Not for: 'is flu rising in Texas?' → get_current_status; 'rank states by COVID wastewater' → get_map; 'is RSV worse in CT than NY?' → compare. Call example: get_data(disease='rsv', view='overall_trend') Scope: US-only aggregate surveillance; relay the precomputed evidence, never re-derive numbers.
One endpoint, the same key, whichever client you use.
~/Library/Application Support/Claude/claude_desktop_config.json (Mac) · %APPDATA%\Claude\claude_desktop_config.json (Windows)
Replace API_KEY with your own key.
Already have an "mcpServers" section in your config? Just add the server entry inside it.
Discovery, routing, credentials, tool scoping and execution logs all happen at the gateway→connections stay ACTIVE with no work from you
PopHIVE MCP runs through a gateway that holds the credentials, scopes the access and records every call.
Managed auth, hosted MCP servers, and every Gmail tool your agent needs.
Free to start.
