who-gho
Provides access to World Health Organization Global Health Observatory data, enabling queries of global health statistics and indicators without authentication.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@who-ghoWhat is the prevalence of diabetes in adults globally?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
WHO GHO — World Health Organization Global Health Observatory
The World Health Organization's GHO database. ~3,000 health-related indicators across 194 member states: mortality, disease prevalence, healthcare workforce, immunization, environmental health, NCDs, communicable diseases, demographics. The canonical international health-data source. Free, no auth.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
Why this matters for AI agents
For international comparisons of health indicators or country-level public-health snapshots, WHO GHO is the source. Where CDC is US-focused, WHO is global. Pair with World Bank (development indicators) and IMF (macro) for full country-level analysis.
Common flows:
Country indicator. "Life expectancy in Brazil?" → indicator + country query.
Cross-country comparison. Same indicator across multiple countries.
Time series. Indicator over years for trend analysis.
Indicator browse. "What does WHO publish on diabetes?" → search the indicator catalog.
Related MCP server: mcp-uk-ons
Auth
None. WHO GHO is fully public, free.
Indicator categories
Major categories (each with dozens to hundreds of indicators):
Mortality and life expectancy
Communicable diseases (HIV, TB, malaria, COVID-19, vaccine-preventable)
Non-communicable diseases (cardiovascular, cancer, diabetes, mental health)
Maternal and child health
Health workforce (physicians, nurses, beds per 1000)
Environmental health (air pollution, water/sanitation access)
Health systems financing
Risk factors (tobacco, alcohol, BMI, blood pressure)
Common pitfalls
Country reporting quality varies. Wealthy countries report comprehensively; lower-income countries have data gaps and longer lags. Some indicators are WHO-modeled estimates filling country reporting gaps.
Disaggregation availability. "Indicator X for country Y" may not break down by sex, age, or urban/rural. Check whether the disaggregation you want exists before building queries that depend on it.
Definition shifts. WHO occasionally revises indicator methodology (e.g., changing definition of "stunting" cut-points). Long time series across methodology changes need annotation.
Lag. Most WHO data lags 1-3 years. Recent year may have only modeled estimates. For real-time outbreak data, use WHO's separate disease-surveillance feeds.
Country naming. WHO uses ISO 3-letter codes. Some politically-disputed entities (Taiwan, Palestine, Kosovo) have inconsistent treatment in headline data; check coverage explicitly.
Population denominator. Per-capita rates are usually computed against UN population estimates. Different sources (UN vs. national stats) can differ slightly, especially for fast-growing populations.
WHO regions. WHO groups countries into 6 regions (Africa, Americas, Eastern Mediterranean, Europe, Southeast Asia, Western Pacific). These don't match World Bank or other regional groupings.
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"who-gho": {
"url": "https://gateway.pipeworx.io/who-gho/mcp"
}
}
}What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/who-gho/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Who Gho data" })The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
No MCP client? Call it over HTTP
curl -X POST https://gateway.pipeworx.io/v1/tools/get_indicators \
-H 'Content-Type: application/json' \
-d '{"query":"life expectancy"}'No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/get_indicators. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.
This server cannot be deployed
Maintenance
Related MCP Connectors
Query 29,500+ World Bank development indicators for 200+ countries across 60+ years.
Search and query 1,500+ OECD statistical datasets via SDMX. Keyless.
Ask data questions in natural language. Get SQL, insights, and charts from your databases.
Macroeconomic and other official data from 170+ publishers, resolved from natural language with provenance.
Related MCP Servers
- AlicenseBqualityDmaintenanceProvides access to the World Health Organization's Global Health Observatory data, enabling AI assistants to search, retrieve, and analyze comprehensive health indicators, country statistics, disease burden data, and regional health trends through WHO's OData API.1MIT
- AlicenseNot gradedqualityCmaintenanceEnables querying UK Office for National Statistics datasets and their editions through natural language, with no authentication required.1 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables access to Our World in Data charts and indicators through natural language queries via Pipeworx gateway.2 npm1MIT
- AlicenseNot gradedqualityAmaintenanceQuery WHO Global Health Observatory data — 3,059 indicators across 194 member states with country, region, year, and sex filters via MCP.69 npm2Apache 2.0