Compatible with every major AI agent and IDE
What is the Harvard WHO Health MCP Server?
Connect to the WHO Global Health Observatory (GHO) API — the world's most comprehensive source of global health statistics.
What you can do
- Health Indicators — Search 1000+ indicators across all health domains
- Life Expectancy — Track life expectancy at birth by country
- Immunization — DTP3, measles, polio, BCG, and hepatitis B coverage
- Infectious Diseases — HIV/AIDS prevalence, TB incidence, malaria estimates
- NCDs — Diabetes, obesity, hypertension, tobacco, and alcohol data
- Maternal Health — Maternal mortality ratios and reproductive health
- Health Workforce — Physicians, nurses, dentists, pharmacists per 10,000 pop.
- Health Expenditure — Per capita spending in PPP dollars
- Water & Sanitation — WASH indicators for safe water and sanitation
- Country Comparison — Compare any indicator across multiple countries
Who is this for?
- Public Health Researchers — global health trends and burden of disease
- Epidemiologists — disease surveillance and outbreak analysis
- Policy Makers — evidence-based health policy decisions
- Global Health Students — coursework and thesis research
Built-in capabilities (16)
Provide a comma-separated list of ISO 3-letter country codes. Returns the most recent 10 years of data for each country. Compare a health indicator across countries
Returns ISO codes and country names for use with other indicator queries. Get list of WHO member countries
Useful for understanding how to filter and disaggregate health data. Get WHO data dimensions metadata
This indicator measures how much each country spends on healthcare, adjusted for purchasing power. Get health expenditure data
Supported types: "physicians", "nurses", "dentists", "pharmacists". Get health workforce density data
Tracks the percentage of the population living with HIV, a critical indicator for public health programs and resource allocation. Get HIV/AIDS prevalence data
Supported shortcuts: "dtp3" (diphtheria-tetanus-pertussis), "measles", "polio", "bcg", "hepb3". Or use a WHO indicator code directly. Get immunization coverage data
g. "USA", "BRA", "GBR", "CHN", "IND"). Returns country, year, value, confidence intervals, and sex disaggregation. Get time-series data for a WHO indicator
This is one of the most fundamental indicators of population health. Get life expectancy data
Essential for tracking the global burden of malaria, particularly in sub-Saharan Africa and Southeast Asia. Get malaria case estimates
This measures the number of maternal deaths per 100,000 live births, a critical indicator of reproductive health and healthcare quality. Get maternal mortality data
Common indicator codes: "NCDMORT3070" (NCD mortality), "CHILDMORTALITY" (under-5), "MATERNALMORTALITY". Use search_indicators to find specific codes. Get mortality data by cause
Supported shortcuts: "diabetes" (prevalence), "obesity" (BMI ≥30), "blood_pressure" (hypertension), "tobacco" (smoking), "alcohol" (consumption). Or use a WHO code. Get non-communicable disease data
TB remains one of the top infectious disease killers worldwide, and this data tracks progress toward elimination. Get tuberculosis incidence data
Supported types: "water" (safely managed drinking water), "sanitation" (safely managed sanitation), "hygiene" (basic hygiene facilities). Get water and sanitation data
Returns indicator codes and names. Use the indicator code with get_indicator_data to retrieve time-series data. Search 1000+ WHO health indicators
Why AutoGen?
AutoGen enables multi-agent conversations where agents negotiate, delegate, and collaboratively use Harvard WHO Health tools. Connect 16 tools through Vinkius and assign role-based access. a data analyst queries while a reviewer validates, with optional human-in-the-loop approval for sensitive operations.
- —
Multi-agent conversations: multiple AutoGen agents discuss, delegate, and collaboratively use Harvard WHO Health tools to solve complex tasks
- —
Role-based architecture lets you assign Harvard WHO Health tool access to specific agents. a data analyst queries while a reviewer validates
- —
Human-in-the-loop support: agents can pause for human approval before executing sensitive Harvard WHO Health tool calls
- —
Code execution sandbox: AutoGen agents can write and run code that processes Harvard WHO Health tool responses in an isolated environment
Harvard WHO Health in AutoGen
Harvard WHO Health and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Harvard WHO Health to AutoGen through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Harvard WHO Health in AutoGen
The Harvard WHO Health MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 16 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in AutoGen only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Harvard WHO Health for AutoGen
Every tool call from AutoGen to the Harvard WHO Health MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Do I need an API key?
No. The WHO GHO API is completely free and public. No authentication required.
How many countries does WHO track?
The WHO Global Health Observatory tracks health data for all 194 Member States, plus territories and regions. Data spans from the 1990s to the present with annual updates.
What types of health data are available?
Over 1,000 indicators across mortality, morbidity, immunization, NCDs (diabetes, obesity), infectious diseases (HIV, TB, malaria), maternal health, health workforce, expenditure, water and sanitation, and more.
How does AutoGen connect to MCP servers?
Create an MCP tool adapter and assign it to one or more agents in the group chat. AutoGen agents can then call Harvard WHO Health tools during their conversation turns.
Can different agents have different MCP tool access?
Yes. AutoGen's role-based architecture lets you assign specific MCP tools to specific agents, so a querying agent has different capabilities than a reviewing agent.
Does AutoGen support human approval for tool calls?
Yes. Configure human-in-the-loop mode so agents pause and request approval before executing sensitive MCP tool calls.
McpWorkbench not found
Install: pip install "autogen-ext[mcp]"
Explore More MCP Servers
View all →
AeroAPI (FlightAware)
5 toolsTrack global flights — audit departures, arrivals, and airports via IA.

HackEDU (Security Journey)
10 toolsAutomate security training via HackEDU — manage users, track progress, and integrate vulnerability data directly from any AI agent.

Getty Images
10 toolsManage stock media via Getty Images — search millions of creative and editorial photos, handle video discovery, and download assets directly from any AI agent.

GoCardless
12 toolsCollect recurring payments directly from bank accounts with automated direct debit that reduces failed payment rates.
