{
  "markdown": "# World Bank — Development Indicators and Country Data\n\nThe 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.\n\nPart of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1476+ live data sources.\n\n## Why this matters for AI agents\n\nFor 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](/docs/reference/imf) (macro/fiscal) with development-specific coverage (WDI, EdStats, GenderStats, etc.).\n\nCommon flows:\n\n- **Indicator lookup.** \"GDP per capita PPP for India\" → World Bank indicator `NY.GDP.PCAP.PP.CD` for India.\n- **Country comparison.** Same indicator across multiple countries.\n- **Theme browsing.** Education indicators, health indicators, environment indicators, etc.\n\n## Auth\n\nNone. World Bank Open Data is fully public, free.\n\n## Indicator code structure\n\nWorld Bank indicator codes follow a domain.theme.metric pattern:\n\n| Code | Indicator |\n|---|---|\n| `NY.GDP.MKTP.CD` | GDP (current US$) |\n| `NY.GDP.PCAP.PP.CD` | GDP per capita, PPP (current intl $) |\n| `SP.POP.TOTL` | Total population |\n| `SE.PRM.ENRR` | Primary school enrollment, gross % |\n| `EG.ELC.ACCS.ZS` | Access to electricity, % of population |\n| `SI.POV.GINI` | Gini index |\n| `EN.ATM.CO2E.PC` | CO2 emissions per capita |\n\nSearch the catalog when you don't know the code.\n\n## Country and country-group codes\n\nWorld Bank uses ISO 3-letter codes (USA, BRA, IND) plus aggregate codes:\n\n- `WLD` — World\n- `EUU` — European Union\n- `LMC` — Lower middle income\n- `OED` — OECD members\n- `SSA` — Sub-Saharan Africa\n\nAggregate codes are useful for \"how does X compare to its peer group?\" questions.\n\n## Common pitfalls\n\n- **Indicator deprecation.** World Bank periodically retires/replaces indicators. The API marks deprecated ones; prefer current ones for new analysis.\n- **Coverage gaps.** Not every country reports every indicator every year. The API returns nulls for missing data. Compute aggregates carefully.\n- **Vintages.** Indicator values can be revised. Cite the vintage if precision matters.\n- **Real vs nominal.** Many financial indicators come in both nominal (current dollars) and real (constant dollars). The `.CD` suffix is current dollars; `.KD` is constant.\n- **PPP vs market exchange rate.** Cross-country GDP comparison should use PPP for most \"how rich is X\" questions; market rates for \"what does X export\" questions.\n- **Data freshness.** World Bank consolidates from member-country reporting; lag varies. Most recent year for many indicators is 1–2 years prior. Check data availability before promising \"current.\"\n\n## Quick Start\n\nAdd to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):\n\n```json\n{\n  \"mcpServers\": {\n    \"worldbank\": {\n      \"url\": \"https://gateway.pipeworx.io/worldbank/mcp\"\n    }\n  }\n}\n```\n\n### What this endpoint actually serves\n\n`tools/list` at `https://gateway.pipeworx.io/worldbank/mcp` returns the tools in the table\nabove **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,\n`discover_tools`, `search_within`, `remember`/`recall` and the rest of the\ngateway-wide set. So the tool count you see is larger than this table: a\nsingle-pack endpoint currently lists roughly 30 shared tools alongside the\npack's own. The connection's `initialize` response states its exact scope, and\nis the authoritative answer for a given day.\n\nThis is deliberate, not multiplexing by accident. The meta-tools are what let a\nscoped connection answer a question this pack does not cover — via\n`ask_pipeworx`, which routes across the whole catalog — without you adding a\nsecond MCP server. There is currently no way to mount a pack endpoint without\nthem; if the extra schemas cost you more context than the routing is worth,\nconnect to the full gateway once rather than to several pack endpoints.\n\nOr connect to the full Pipeworx gateway to get every pack's tools listed\ndirectly, instead of just this one's:\n\n```json\n{\n  \"mcpServers\": {\n    \"pipeworx\": {\n      \"url\": \"https://gateway.pipeworx.io/mcp\"\n    }\n  }\n}\n```\n\nBoth URLs reach the same gateway and the same 1476+ data sources. The\nonly difference is which pack's tools are listed **directly**; `ask_pipeworx`\nreaches all of them from either one.\n\n## Using with ask_pipeworx\n\nInstead of calling tools directly, you can ask questions in plain English —\nthis works on the pack endpoint above as well as on the full gateway:\n\n```\nask_pipeworx({ question: \"your question about Worldbank data\" })\n```\n\nThe gateway picks the right tool and fills the arguments automatically.\n\n## More\n\n- [Docs and guides](https://pipeworx.io/docs)\n- [pipeworx.io](https://pipeworx.io)\n\n## License\n\nMIT\n",
  "bytes": 4953,
  "sha": "1743928c01b5ffa1d87304ae4205b0da82ca5c68b7ac27312908bd78cad091ee",
  "repo_slug": "pipeworx-io/mcp-worldbank",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_pipeworx_io_worldbank_ce13dae0/readme"
}