Pandemic Biosurveillance MCP Server

Stochastic metapopulation epidemic simulation and phylodynamic analysis for pandemic preparedness, public health research, and outbreak response. This MCP server orchestrates 16 data sources spanning WHO health data, clinical trials, FDA/EMA drug databases, biomedical literature, ecological species data, environmental monitoring, and geospatial intelligence to power 8 mathematically rigorous epidemic modeling tools. Implements Gillespie SSA, particle MCMC, birth-death skyline phylodynamics, augmented synthetic control, mean-field game theory, and MaxEnt species distribution modeling.

What data can you access?

Data Point	Source
Global health indicators and disease burden	WHO Global Health Observatory
Active clinical trials for vaccines and therapeutics	ClinicalTrials.gov
Adverse drug events and safety signals	openFDA FAERS
European medicines authorizations	EMA
Biomedical literature and citation data	PubMed, OpenAlex, Europe PMC
Species distribution and conservation status	IUCN Red List, GBIF
Natural disaster alerts and impact estimates	GDACS
Weather, climate, and air quality data	NOAA, OpenAQ
Disaster declarations and emergency management	FEMA
Country demographics and socioeconomic data	REST Countries, World Bank
Geolocation and spatial data	Nominatim

MCP Tools

Tool	Price	Description
simulate_epidemic_metapopulation	$0.04	Stochastic SEIR-HCD metapopulation simulation via Gillespie SSA on radiation mobility network
infer_parameters_pmcmc	$0.04	Infer R0, latent period, IFR, hospitalization rate via particle MCMC with alive particle filter
estimate_phylodynamic_Re	$0.04	Estimate effective reproduction number Re over time using birth-death skyline model
evaluate_intervention_causality	$0.04	Evaluate causal NPI/pharmaceutical intervention effects via augmented synthetic control
compute_vaccination_equilibrium	$0.04	Compute vaccination Nash equilibrium vs social optimum via mean-field game theory
forecast_variant_fitness	$0.04	Forecast variant frequency trajectories using multinomial logistic regression
assess_zoonotic_spillover	$0.04	Assess zoonotic spillover risk using MaxEnt species distribution modeling
model_seasonal_waning_dynamics	$0.04	Model seasonal Re forcing with power-law antibody waning dynamics

Data Sources

• WHO Global Health Observatory -- Global disease burden, mortality, and health system indicators
• ClinicalTrials.gov -- Vaccine and therapeutic trial data with enrollment, phases, and outcomes
• openFDA Drug Events -- Adverse event reporting for pharmaceutical interventions
• EMA Medicines -- European authorized medicines and regulatory status
• PubMed -- Biomedical literature for epidemiological evidence
• OpenAlex -- Academic publication metadata and citation networks
• Europe PMC -- European biomedical literature and preprints
• IUCN Red List -- Species conservation status and distribution for zoonotic host assessment
• GBIF -- Global biodiversity occurrence data for species distribution modeling
• GDACS -- Global disaster alerting for events affecting health infrastructure
• NOAA -- Weather and climate data for seasonal forcing analysis
• OpenAQ -- Air quality monitoring data as environmental health proxy
• FEMA -- US disaster declarations and emergency management data
• REST Countries -- Country demographics, population, and geographic data
• Nominatim -- Geolocation and spatial reference data
• World Bank -- Development indicators and socioeconomic data

How the scoring works

Each tool implements a distinct mathematical model:

Gillespie SSA Metapopulation (Tool 1) simulates stochastic epidemic spread across connected populations using 7 compartments (S, E, I, R, H, C, D). Inter-population transmission follows the radiation mobility model (Simini et al. 2012). Tau-leaping approximation enables efficient simulation across 20+ populations.

Particle MCMC (Tool 2) infers epidemic parameters from observed data using an alive particle filter for unbiased likelihood estimation. Metropolis-Hastings acceptance with Gelman-Rubin R-hat convergence diagnostics ensures reliable posterior distributions for R0, latent period, IFR, and hospitalization rate.

Birth-Death Skyline (Tool 3) estimates Re trajectories using piecewise-constant birth rates cross-validated with epidemiological estimates via Bayesian model averaging with thermodynamic integration.

Augmented Synthetic Control (Tool 4) estimates causal intervention effects by constructing synthetic counterfactuals with conformal prediction intervals for valid uncertainty quantification.

Mean-Field Game (Tool 5) solves coupled HJB backward and Fokker-Planck forward PDEs to find vaccination Nash equilibrium. Quantifies the free-rider gap between individual rational behavior and social optimum.

Multinomial Logistic Regression (Tool 6) forecasts variant frequency trajectories. Fitness advantages are estimated as selection coefficients on a Maynard-Smith fitness landscape.

MaxEnt Species Distribution (Tool 7) models zoonotic spillover probability as P(host) x P(contact) x P(adaptation) using species occurrence data and deforestation frontier kernel density estimation.

Fourier Seasonal Forcing (Tool 8) models seasonal Re oscillation with power-law antibody waning (Khoury et al. 2021) to compute optimal booster timing and seasonal wave predictions.

How to connect this MCP server

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "pandemic-biosurveillance": {
      "url": "https://pandemic-biosurveillance-mcp.apify.actor/mcp"
    }
  }
}

Programmatic (HTTP)

curl -X POST https://pandemic-biosurveillance-mcp.apify.actor/mcp \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_APIFY_TOKEN" \
  -d '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"simulate_epidemic_metapopulation","arguments":{"query":"H5N1 avian influenza pandemic"}},"id":1}'

This MCP also works with Cursor, Windsurf, Cline, and any other MCP-compatible client.

Use cases for pandemic biosurveillance intelligence

Outbreak Response Simulation

Simulate how a novel pathogen would spread across connected populations using the stochastic metapopulation model. Estimate peak timing, herd immunity thresholds, and geographic spread patterns to inform resource allocation.

Vaccination Strategy Optimization

Use the mean-field game equilibrium to understand vaccination incentive structures. Quantify the free-rider gap and identify optimal age-group prioritization strategies that balance individual and social welfare.

Variant Tracking and Forecasting

Forecast which pathogen variants will dominate using fitness advantage estimation. Identify high-risk escape mutations and track variant competition dynamics to inform vaccine strain selection.

Zoonotic Spillover Risk Mapping

Identify geographic hotspots where deforestation frontiers intersect with high-diversity bat or rodent populations. Assess spillover probability for pandemic preparedness planning and surveillance resource deployment.

Intervention Impact Assessment

Estimate the causal effect of lockdowns, mask mandates, or vaccination campaigns using augmented synthetic control methodology. Quantify lives saved and transmission reduction with proper uncertainty quantification.

Seasonal Wave Prediction

Model seasonal forcing of respiratory pathogen transmission with antibody waning dynamics. Compute optimal booster timing to minimize population-level susceptibility during peak transmission seasons.

How much does it cost?

This MCP uses pay-per-event pricing. Each tool call costs $0.04.

The Apify Free plan includes $5 of monthly platform credits, which covers 125 tool calls.

Example Use	Approximate Cost
Single epidemic simulation	$0.04
Parameter inference for an outbreak	$0.04
Full suite of 8 analyses for one pathogen	$0.32

Note: Each tool runs up to 16 actors in parallel, making the per-tool cost extremely efficient for the data volume processed.

How it works

1. You call a tool with a disease, pathogen, or outbreak query
2. Up to 16 Apify actors run in parallel fetching data from WHO, clinical trials, literature, ecological databases, environmental monitoring, and geospatial sources
3. An epidemic network is constructed linking health data, species distributions, environmental factors, and geographic context
4. The mathematical model runs on the constructed network -- Gillespie SSA, particle MCMC, birth-death skyline, or whichever algorithm the tool implements
5. Structured results are returned with model outputs, convergence diagnostics, and supporting data

FAQ

Q: Are the simulations based on real data? A: Yes. Each tool fetches live data from 16 sources to parameterize the models. The simulation parameters are derived from WHO health indicators, clinical trial data, species distributions, and environmental conditions relevant to the query.

Q: How accurate are the epidemic forecasts? A: The models implement published mathematical frameworks (Gillespie SSA, Stadler birth-death, Abadie synthetic control) with proper convergence diagnostics. Results should be interpreted as scenario analysis informed by current public data, not clinical-grade predictions.

Q: Can this replace public health surveillance systems? A: No. This provides computational modeling capabilities powered by public data sources. It complements but does not replace dedicated public health surveillance infrastructure.

Q: What pathogens can I analyze? A: Any pathogen with public health data -- respiratory viruses (influenza, SARS-CoV-2), vector-borne diseases, zoonotic threats, and emerging infectious diseases.

Q: Is it legal to use this data? A: All 16 data sources are publicly available databases from international organizations and government agencies. See Apify's guide on web scraping legality.

Q: Can I combine this with other MCPs? A: Yes. Use alongside the Pharma Pipeline Intelligence MCP for vaccine/therapeutic pipeline tracking or the Travel Risk Intelligence MCP for destination health risk assessment.

Related MCP servers

MCP Server	Description
ryanclinton/pharma-pipeline-intelligence-mcp	Drug and vaccine pipeline competitive intelligence
ryanclinton/travel-risk-intelligence-mcp	Travel destination health and safety risk
ryanclinton/climate-economic-nexus-mcp	Climate and environmental economic analysis

Integrations

This MCP server is built on the Apify platform and supports:

• Apify API for programmatic access and automated outbreak monitoring
• Scheduled runs via Apify Scheduler for recurring surveillance
• Webhooks for triggering alerts when Re estimates exceed thresholds
• Integration with 200+ Apify actors for extending epidemiological data coverage