Download or re-download the public GHED workbook and rebuild SQLite.

Return cache status and WHO source-document details; initializes an empty cache.

The first call may take minutes. Run ghed-mcp --warm-cache in a terminal first if the MCP client has a short tool timeout. Use check_for_updates to check for newer WHO data without downloading the workbook.

Compare the local cache source document with the current GHED all-data file.

Return workbook version lines and cache provenance.

Explain how GHED variables are organized and how to choose the right series.

Curated GHED topic index mapping common user requests to variable codes.

Research patterns seen in GHED-using literature, with recommended variables.

Map a natural-language research question to likely GHED variables and cautions.

List GHED variable category counts from the Codebook.

List headline GHED indicators only (category_1 = INDICATORS).

List all GHED Codebook variables, optionally filtered by category.

Search headline indicators; use search_variables for detailed SHA series.

This is substring search, not semantic search. Use a short fragment such as 'out-of-pocket', 'GGE' or 'che_gdp', not a full research question. If no match, shorten the query or use topics_index. category_1=None searches all variables.

Search all Codebook variables; use search_indicators for headline measures.

This is substring search. Use a short code/name fragment, not a full question. An empty result can mean the wording did not match; shorten the query or use topics_index before concluding that a variable is unavailable.

List countries and territories available in GHED, optionally by group.

country_group accepts curated codes (LAC, OECD, LDC, SSA, …) and intersects with region / income when more than one is set, so country_group="LAC", income="High" returns LAC HICs.

List GHED country grouping values by region and World Bank income class.

List Decilion's curated country groupings (WB regions, LDCs, OECD).

Returns groups beyond GHED's built-in WHO regions and World Bank income classes — World Bank geographic regions, the UN Least Developed Countries list, and OECD membership. Use the returned members lists with the countries parameter on data tools, or pass the group code to resolve_country_group_membership to get just the ISO3 list.

Resolve a curated group code to its ISO3 member list.

Accepts canonical codes (LAC, SSA, LDC, OECD, …), official WB region codes (LCN, SSF, …), and common spellings ("Latin America and Caribbean", "Sub-Saharan Africa", "Least Developed Countries").

Find ISO3 country codes by name, alias, or code fragment.

Return Codebook metadata for one GHED indicator.

Return source, data-type and estimation notes from the Metadata sheet.

If no indicator-specific notes exist, query country alone for broader notes. Country notes are context, not proof of the selected indicator's data type or the cause of a trend. Empty metadata does not establish data quality.

Summarize availability for indicators before building a research panel.

Return known additive child relationships for a GHED variable.

Explain whether a variable is a total, component, ratio/share, or context series.

Check a current-NCU accounting total for one country-year.

Use additive_hierarchy to choose a relationship. If complete is false, the identity cannot be validated even when observed components nearly sum to the total. Missing components are not zero or implicitly included elsewhere.

Build a tidy long panel for multiple GHED variables across countries and years.

country_group accepts curated codes ("LAC", "OECD", "LDC", "SSA", …) that resolve to ISO3 lists; combine freely with countries, region, and income (filters apply via SQL AND).

Build export-ready CSV data, codebook, and README text for a research extract.

Fetch one GHED indicator with optional country and year filters.

Spatial filters compose: country (singular), countries (list), and country_group (curated, e.g. "LAC") merge into a single country list, and region / income further constrain via SQL AND.

One GHED indicator across countries, returned as tidy rows or CSV.

Pass either an explicit countries list or a curated country_group (e.g. "LAC", "OECD", "LDC", "SSA") — or both, in which case they are merged. See list_curated_country_groups for available groups.

Compare one GHED indicator across a country group (curated, regional, or income-based).

Pass at least one of country_group (e.g. "LAC", "OECD", "LDC"), region, or income. Multiple filters compose via SQL AND, so country_group="LAC", income="High" returns LAC HICs.

Summarize an indicator within a country group (curated, regional, or income).

Pass at least one of country_group ("LAC", "OECD", "LDC", …), region, or income.

Compute first/latest trends for one indicator; use compare_trends for several.

percent_change and cagr are fractions (0.10 = 10%). absolute_change is in the indicator's units, or percentage points for shares. Inspect actual first/latest years and change_units before interpreting or ranking results.

Compute first/latest summaries for several indicators; use indicator_trend for one.

percent_change and cagr are fractions (0.10 = 10%); absolute changes in shares are percentage points. Check each item's years, warnings and limits.

Rank countries by change; use indicator_trend for unranked summaries.

metric='percent_change' and 'cagr' use fractions (0.10 = 10%), not percentage units. 'absolute_change' uses percentage points for shares, otherwise the indicator's original units. Compare actual first/latest years and change_units.

Summarize metadata, availability, and cautions for an indicator/filter.

Latest headline health-expenditure values for one country.