@cyanheads/worldbank-mcp-server
Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.
Needs to start: nothing
Returns a result when called with no setup: 4 of 5 tools tried
Contacts while installing and starting: nothing
What it contacted
Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.
Starting it
npx -y @cyanheads/worldbank-mcp-server@0.6.1
Installing a package runs its code. Use a sandbox for anything you have not read.
Calling its tools
5 tools that take no input and look read-only were called once with nothing. 4 returned a result.
worldbank_list_topics | Returned a result 0.2 s · 12,720 characters |
worldbank_list_sources | Returned a result under 0.1 s · 7,487 characters |
worldbank_list_countries | Returned a result under 0.1 s · 9,591 characters |
worldbank_search_indicators | No usable answer tool reported an error: Error: At least one of query, topic_id, or source_id must be provided. Recovery: Provide a keyword query, a topic_id from worldbank_lis |
worldbank_search_projects | Returned a result 0.2 s · 51,759 characters |
During the calls (not necessarily because of them) it first contacted: api.worldbank.org, search.worldbank.org.
Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.
What its tools tell an agent
In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.
Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.
Tools
worldbank_list_topics
List all 21 World Bank thematic topics (Economy & Growth, Health, Education, and others) with descriptions. Use it to browse the indicator space by theme or to find a topic_id for worldbank_search_indicators.
worldbank_list_sources page, per_page
List the 70+ World Bank data sources (datasets), such as World Development Indicators, International Debt Statistics, and Doing Business. Returns source IDs and names for use as source_id in worldbank_search_indicators, worldbank_get_data, and worldbank_list_countries, one page at a time.
worldbank_list_countries source_id, region, income_level, lending_type, include_aggregates, filter, page, per_page
List countries and regional aggregates with metadata: ISO codes, region, income level, lending type, capital, and coordinates. Filter by region code (e.g. EAS, SSF, NAC), income level (LIC, LMC, UMC, HIC), and lending type (IDX for IDA, IBD for IBRD, IDB for Blend), or by text with filter, which matches words in each entry's id and name; filters combine by AND. Aggregate entries are excluded by default, leaving individual countries only; set include_aggregates=true to also return region, income group, and world aggregate entities. With source_id, lists that dataset's own entities instead, and filter finds them by name or code (source_id=50 with filter="Kenya" returns Kenya and its provinces).
worldbank_get_country country_code
Fetch metadata for one country or aggregate entity: ISO codes, region, income level, lending type, capital, and coordinates. Accepts an ISO2 code (US, DE), an ISO3 code (USA, DEU), or a World Bank aggregate code (EAS, HIC, WLD); "all" and lists of codes are rejected. Use worldbank_list_countries to browse valid codes.
worldbank_search_indicators query, topic_id, source_id, page, per_page
Search the 29,500+ World Bank indicator catalog by keyword, topic, or source, returning indicator IDs and metadata for worldbank_get_data. Provide at least one of query, topic_id, or source_id; a topic and a source together narrow to indicators in both. A keyword query matches every term against indicator ID, name, and full description, in any word order, across the whole catalog or the whole selected topic or source; punctuation is ignored, so the query needs at least one letter or digit. Exact ID or name matches rank first, then names starting with the phrase as whole words, then whole-phrase matches, then matches where every term is a whole word of the ID or name, then other ID/name matches, then description-only matches; within each of those, World Development Indicators series come first, then other live sources, then archives, and a series comes ahead of its own breakdowns by sex, area, or age. Each indicator ID appears once, even where the catalog publishes it under two sources. Each result carries the first 150 characters of its description; worldbank_get_indicator returns the whole of it. Find topic IDs with worldbank_list_topics and source IDs with worldbank_list_sources.
4 more tools
worldbank_get_indicator indicator_id
Fetch metadata for one World Bank indicator by ID: name, description, unit, source dataset, source organization, and thematic topics. Use worldbank_search_indicators to find the ID when only the concept is known; "all" and lists of IDs are rejected.
worldbank_get_data source_id, indicator_id, countries, date_range, mrv, mrnev, frequency, dimension_value, page, per_page
Query World Bank indicator values for one or more countries across a time range — the primary data-access tool; find indicator_id values with worldbank_search_indicators. Observations carry a null value where data is not available for a country×year cell, which is common for sparse series. Set at most one of date_range (a time window), mrv (the latest N periods across the requested countries), or mrnev (each country's own latest N values). Some series, such as Global Economic Monitor's, publish quarterly or monthly values beside annual ones: frequency picks the form mrv and mrnev select from (annual by default), and a date_range's own form (2024, 2024Q1, 2024M01) picks it for a window. lastUpdated gives the serving source's last update date, the data vintage to cite. For "all" countries, page through the results at up to 1000 per page, since the API returns several hundred entries per indicator. Indicators the standard data endpoint does not serve — WDI Database Archives, PEFA, ICP, GDLD, International Debt Statistics: DSSI, Food Prices for Nutrition — are answered from their own dataset instead; the response then carries sourceScoped, naming that dataset and the release, classification, sector, or counterpart area applied (see dimension_value), because those values can be archived or superseded figures rather than current ones.
worldbank_get_poverty countries, year, poverty_line, welfare_type, reporting_level, ppp_version, fill_gaps, page, per_page
Query poverty and inequality estimates from the World Bank Poverty and Inequality Platform (PIP) for economies and for PIP's own aggregates — World, World Bank regions, income groups, lending groups, and fragility groups. Returns the poverty headcount ratio, poverty gap, and poverty severity at any poverty line, plus mean and median welfare and population. Use it for inequality and distribution questions too — survey-based economy rows carry the Gini coefficient, mean log deviation, polarization, and the ten decile income/consumption shares, because PIP returns poverty and inequality in the same row. PIP is a separate dataset from the WDI series worldbank_get_data reads: it measures welfare in PPP dollars per person per day, at a PPP vintage ppp_version selects, and computes its aggregates at any poverty line, where worldbank_get_data carries only the published lines. Every row reports how it was produced. Nullable estimateType separately identifies actual, nowcast, or projection estimates, while distributionType preserves the source distribution classification (micro, group, or imputed); missing upstream classifications remain null. On an economy, estimationType "survey" rows carry the full inequality block; "interpolation", "extrapolation", and "CMD estimation" rows are gap-filled estimates where no survey covers the year, reporting level, and welfare type, and their gini, mld, polarization, and decileShares are null — a documented gap in the source data, not an error. Aggregate rows (isAggregate true) are "actual", "nowcast", or "projection", add popInPoverty, and carry no distributional block.
worldbank_search_projects query, countries, status, sector, region, financial_type, approved_from, approved_to, include_abstract, page, per_page
Search the World Bank lending portfolio — the individual loans, credits, and grants the Bank finances — by free text, country, region, status, sector, financing window (IBRD, IDA, Grants, Other), and board approval date. Returns the project ID, name, development objective, borrowing country, region, status, board approval and closing dates, the commitment amount in USD with its IBRD, IDA, and grant parts, financing windows, major sectors, the sub-sectors under them with the share of the commitment each carries, and a link to the project page. This is the operations catalogue, not the statistics catalogue: use it for "what is the World Bank funding in Kenya", "which climate adaptation projects are active", or "how much was committed to education in South Asia since 2020". For development statistics and time series, use worldbank_search_indicators and worldbank_get_data instead. sector takes the sub-sector names rows list in sectors[].name, not the majorSectors names — for education commitments, sector: ["Primary Education", "Secondary Education", "Tertiary Education"] rather than a free-text query, which also matches incidental prose. Those are three of the Education sub-sectors, so read sectors[].name on a few matching rows to collect the rest before totalling a whole sector. A project matches when it lists a sector at any share, so a sector total weights each totalCommitment by the percent that sector carries. Countries take the ISO3 or ISO2 codes the other tools take (BRA or BR), and multi-country operations carry a World Bank regional code such as 3W or 3E; WDI aggregates such as SSF or WLD are rejected, since the portfolio lists operations by economy — use region for those. Every filter is an exact match upstream and combines with the others by AND, so a narrow search can legitimately return nothing; when it does, the response says whether the country codes matched anything on their own.
Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.
Install facts
| License | Apache-2.0 |
|---|---|
| Needs | node >=24.0.0 |
| Source | github.com/cyanheads/worldbank-mcp-server |
| Install scripts | None declared by it or anything installed with it. |
| Tarball | sha512-1NCwHw3nSTBUSkL2gTQOj4WiRKLHizSKV8TdJHxuHyyHuemjKukVjTNWS+i2ABNqXbfTFPqs+3p5RcV27phsIw== |
Check this report yourself
This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.
Report as JSONExact text and tokenHow to verify it
Show it on your README
[](https://bragproof.smaverk.com/r/%40cyanheads/worldbank-mcp-server)
New version out? Ask for a fresh report.