Worldbank MCP Server

@cyanheads/worldbank-mcp-server Query 29,500+ World Bank development indicators for 200+ countries across 60+ years via MCP. STDIO or Streamable HTTP. 9 Tools • 2 Metadata Resources • 1 Skill

Public Hosted Server: https://worldbank.caseyjhand.com/mcp

Overview

World Bank Open Data: 29,500+ development indicators, poverty and inequality estimates, and the Bank's lending projects. Search indicators, query country and source-specific time series, pull poverty metrics, and search active and historical projects. No API key required. The published worldbank-guide skill (skill://worldbank-guide/SKILL.md) covers dataset selection, comparable observations, source-specific identifiers, and lending totals.

Tools

Resources

Capability reference

worldbank_list_topics tool

• No input required — returns the complete fixed taxonomy of 21 thematic topics
• Topic IDs (e.g. 1 Agriculture, 3 Economy & Growth) feed topic_id on worldbank_search_indicators

worldbank_list_sources tool

• Paginated list of the 70+ World Bank data sources (datasets); up to 100 per page
• Each entry carries ID, name, short code, last-updated date, and data/metadata availability
• Source IDs (e.g. 2 for World Development Indicators) feed source_id on worldbank_search_indicators, worldbank_list_countries, and worldbank_get_data

worldbank_list_countries tool

• Filters by region code (EAS, SSF, … plus membership groupings such as AFE, EUU, LDC), income level (LIC, LMC, UMC, HIC), and lending type (IDX, IBD, IDB, LNX), combined by AND; up to 300 per page
• Returns ISO codes, region, income level, lending type, capital, and coordinates; an invalid region or income code is a typed invalid_filter error
• Individual countries only by default — include_aggregates=true adds regional, income-group, and world aggregates, flagged isAggregate
• With source_id, returns that dataset's canonical entities as id, name, and sourceId, including subnational IDs. Global classification filters and include_aggregates=true fail as unsupported_source_filter; the default false does not discard source entities

worldbank_get_country tool

• Accepts one ISO2 (US), ISO3 (USA), or World Bank aggregate code (EAS, HIC, WLD) — all or a list is rejected as multiple_countries
• Returns region, income level, lending type, capital, and coordinates
• Typed country_not_found error with a recovery hint pointing to worldbank_list_countries

worldbank_search_indicators tool

• At least one of query, topic_id, or source_id; every keyword term must match the indicator ID, name, or description, in any order; up to 100 per page
• Ranked exact ID/name matches first, then names starting with the phrase, then looser matches, then description-only ones; World Development Indicators series lead each tier, and a series leads its own breakdowns (SP.DYN.LE00.IN ahead of SP.DYN.LE00.FE.IN)
• Each indicator ID appears once, with the first 150 characters of its description; worldbank_get_indicator returns the whole

worldbank_get_indicator tool

• One indicator ID per call, made of letters, digits, ., _, or - — all, a list, or any other character is rejected
• Returns description, unit, source dataset, source organization, and topics; HTML line breaks in the description are preserved, other markup is stripped
• Typed indicator_not_found error pointing to worldbank_search_indicators

worldbank_get_data tool

• countries as ISO2, ISO3, aggregate codes, WLD, or all alone; at most one of date_range (a year, quarter, or month, or a range of one type), mrv (the latest N periods across the countries), or mrnev (each country's own latest N non-empty values); frequency (annual, quarterly, monthly) picks the period form on series that publish several, while a date window's own form selects it; up to 1,000 observations per page
• Rows carry both country codes, isAggregate, and value: null for a missing cell, with nullCount per page and lastUpdated, the source's data vintage; every date_range, mrv, and mrnev read is checked for another query's cached answer and re-read once, and one that fails twice is an upstream_inconsistent error rather than a served result
• Indicators the standard endpoint doesn't serve (WDI Database Archives, PEFA, ICP, GDLD, International Debt Statistics: DSSI, Food Prices for Nutrition) come from their own dataset, disclosed in sourceScoped with the release, classification, sector, or counterpart area applied (dimension_value)
• source_id selects a dataset explicitly; discover its entity IDs with the same source on worldbank_list_countries. Source-only entities retain their opaque countryCode and an empty countryIso3; sourceId names the serving dataset when known. Unknown or unsupported sources fail as source_not_found / source_not_queryable

worldbank_get_poverty tool

• Economies by ISO3 or ISO2 code, including those PIP publishes only as model estimates (AFG), plus PIP's aggregates: WLD, regions (SSF, AFE), income groups (LMIC/LMC), lending groups (IDX, IDB, IBD, REST), and fragility groups (FCVY, FCVN; WDI's FCS is rejected with FCVY guidance, without asserting the same membership); year as a year, all, or MRV; any poverty_line, defaulting to the applied PPP vintage's international line; up to 1,000 estimates per page
• Headcount, gap, severity, and Watts index, plus the Gini coefficient, mean log deviation, polarization, and decile shares on survey rows; estimationType separates survey rows from gap-filled ones, whose inequality fields are null, and isAggregate flags aggregate rows
• estimateType preserves actual/projection/nowcast provenance independently of estimationType; distributionType preserves micro/group/imputed classification. Both remain null when upstream supplies none
• fill_gaps (default true) includes gap-filled years; welfare_type and reporting_level narrow economy results, and ppp_version picks the PPP vintage

worldbank_search_projects tool

• Free-text query combined by AND with countries (ISO3, ISO2, or a World Bank regional code such as 3A), region, sector, status, financial_type, and a board-approval window (approved_from/approved_to); up to 1,000 projects per page, newest approval first
• Returns ID, name, country, region, status, dates, the commitment amount with its IBRD, IDA, and grant parts, financing windows, sectors, and a URL; countryCodes chain into the other tools, a bad code or unparseable query is a typed invalid_country_code / invalid_query error, and an empty result names the filter that emptied it
• include_abstract (off by default) adds complete abstracts without changing the page size
• sector accepts an array of names, combining them by OR and with other filters by AND. Bare and FY17 - spellings query both naming forms; codes are not aliases. Unknown names return no matches; blank names and embedded caret separators fail as invalid_sector_name

worldbank://indicator/{indicatorId} resource

• Indicator metadata as application/json — name, description, unit, source dataset, source organization, and topics
• indicatorId comes from worldbank_search_indicators; an unknown ID returns a typed not-found error with a recovery hint, while an upstream outage or timeout keeps its own classification instead of reading as a bad ID

worldbank://country/{countryCode} resource

• Country/aggregate metadata as application/json — ISO codes, region, income level, capital, coordinates
• Accepts one ISO2, ISO3, or World Bank aggregate code — all or a list is rejected; an unknown code returns a typed not-found error, distinct from a transient upstream failure

Features

Built on @cyanheads/mcp-ts-core: stdio and Streamable HTTP transports, pluggable auth (none / jwt / oauth), swappable storage (in-memory, filesystem, Supabase, Cloudflare KV/R2/D1), structured loggin