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.
Hermes is Nous Research's command-line agent. MCP servers are declared in its YAML config and reloaded without a restart.
This guide connects PopHIVE MCP to Hermes through MewCP, so Hermes can use PopHIVE MCP's 7 tools, like get_overview, get_current_status and get_trend.
PopHIVE MCP needs no credentials, but every call still runs through MewCP: scoped, checked and logged like any other.
More apps
Full Google Search Console control for search analytics, sitemaps, sites, and URL inspection, directly from your AI workflows. This MCP server exposes the Google Search Console API for querying search traffic data, managing sitemaps and site properties, and inspecting the indexing status of any URL. It is built for SEO teams monitoring search performance, developers automating sitemap and property management, and analysts pulling search traffic data into reporting pipelines.
Manage courses, assignments, rosters and student activity within Google Classroom. Create learning workflows, track submissions and organize educational content across classrooms.
AI's impact on real-world sectors, as a structured record for agents: source-linked headlines placed in one of 18 sectors (healthcare, law, retail, government, defense and more), with outlet, country and time, since June 2026
MoSPI MCP Server provides AI agents access to official Indian government statistics from the Ministry of Statistics and Programme Implementation, covering 500+ indicators across employment, prices, industry, national accounts, health, education, trade, and more.
Other clients
PopHIVE MCP works the same way in every client below. Pick yours for its own guide.
Free to start.
Scope access to the exact PopHIVE MCP tools and accounts you allow, work and personal side by side. Anything outside that scope is refused at call time, even when the model asks for it.
Each call is logged: what ran, on which account, and whether it worked. Failures come back structured, so the agent knows whether to retry instead of guessing.
Every app sits behind one secure MCP URL, and there is no server for you to deploy or keep running. Add an integration in the dashboard and it is live on the next call, with no config to change and no new credentials to wire up. Tools load only when a task needs them, so your agent stays fast and focused however many apps you connect.
Edit config.yaml in your Hermes config directory (~/.hermes).
Put this under the top-level "mcp_servers:" key.
Run /reload-mcp in Hermes, or start a fresh session. Sign in when the browser window opens.
Start a new chat and ask: "List the tools you can use from MewCP." You should see your connected apps.
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.
