
Wraps the World Bank Data API v2 so you can pull development indicators, country statistics, and economic data without leaving your AI workflow. No authentication needed. Part of the Pipeworx gateway ecosystem, which means you can either connect to this single source or tap into their full network of 250+ APIs through one endpoint. The ask_pipeworx tool lets you query in plain English instead of constructing API calls manually. Useful when you're building agents that need access to GDP figures, population stats, poverty rates, or any other World Bank dataset without dealing with HTTP requests and response parsing yourself.
The World Bank Open Data API. Thousands of development, economic, social, and demographic indicators for every country. Time series going back decades. The canonical source for cross-country comparisons of poverty, education, health, gender, environment, infrastructure. Free, no auth.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
For development questions, cross-country comparisons of social indicators, or any "how does country X compare on indicator Y" question, the World Bank's database is the right starting point. Complements IMF (macro/fiscal) with development-specific coverage (WDI, EdStats, GenderStats, etc.).
Common flows:
NY.GDP.PCAP.PP.CD for India.None. World Bank Open Data is fully public, free.
World Bank indicator codes follow a domain.theme.metric pattern:
| Code | Indicator |
|---|---|
NY.GDP.MKTP.CD | GDP (current US$) |
NY.GDP.PCAP.PP.CD | GDP per capita, PPP (current intl $) |
SP.POP.TOTL | Total population |
SE.PRM.ENRR | Primary school enrollment, gross % |
EG.ELC.ACCS.ZS | Access to electricity, % of population |
SI.POV.GINI | Gini index |
EN.ATM.CO2E.PC | CO2 emissions per capita |
Search the catalog when you don't know the code.
World Bank uses ISO 3-letter codes (USA, BRA, IND) plus aggregate codes:
WLD — WorldEUU — European UnionLMC — Lower middle incomeOED — OECD membersSSA — Sub-Saharan AfricaAggregate codes are useful for "how does X compare to its peer group?" questions.
.CD suffix is current dollars; .KD is constant.Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"worldbank": {
"url": "https://gateway.pipeworx.io/worldbank/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/worldbank/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.
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 Worldbank data" })
The gateway picks the right tool and fills the arguments automatically.
MIT