Skip to main content
Glama

unhcr-refugees-mcp-server

UNHCR durable solutions

unhcr_get_solutions
Read-onlyIdempotent

Get durable solutions per year (1959 to the latest year) by country of origin and/or asylum: refugees who returned home, refugees resettled to a third country, refugees naturalised, and IDPs who returned. The asylum country means something different per column: the country refugees returned from, the country they were resettled to, the country that naturalised them; IDP returns sit on the origin country itself. Null means the figure was not collected for that country and year, not zero.

Input Schema

NameRequiredDescriptionDefault
limitNoRequested inline rows, 1–1000000 (default 100); values above 500 are clamped to 500 with disclosure. Sorting runs over the full result first; a larger result is staged as a dataframe where dataframes are enabled.
stageNoStage the full result as a dataframe even when it fits inline, e.g. to join it with another unhcr_get_* result in unhcr_dataframe_query. Where dataframes are unavailable it is ignored, and the notice says so.
asylumNoCountry of asylum — where people sought or hold protection; for returns, the country they returned from — as ISO3 codes (DEU, TUR), case-insensitive, same rules as origin. At most 50 codes. Omit to sum every asylum country into one row, or set expand to list each.
expandNoList every country, one row each, for a dimension that origin or asylum leaves unfiltered: origin, asylum, or both. Default none, where an unfiltered dimension is summed into one row. Expanding a dimension that origin or asylum already filters is rejected.none
originNoCountry of origin — where people fled from — as ISO3 codes (SYR, AFG), case-insensitive. ISO 3166 alpha-2 codes (SY) are rewritten to ISO3 and echoed in applied_scope. UNHCR's own codes (GFR) are rejected with the ISO3 to pass instead, and country names are rejected: resolve a name with unhcr_list_reference (topic countries, name_contains). Each listed code returns its own rows; codes are never summed together. At most 50 codes. Omit to sum every origin into one row, or set expand to list each.
sort_byNoOrder of the full result before the inline cut. year (default) orders by year, then origin ISO3, then asylum ISO3; a count field orders largest first, nulls last.year
year_toNoLast year of the window. When omitted, the window runs to the latest published year (latest_year in the result). A year past the latest published year is clamped to it and the clamp is reported.
year_fromNoFirst year of the window. When omitted, the window starts at the dataset's first year. A year before the dataset's first year is clamped to it and the clamp is reported; a window entirely outside the dataset's years is rejected.

Output Schema

NameRequiredDescriptionDefault
capNoThe limit that was applied.
rowsNoInline rows, sorted, up to limit.
errorNoPresent when the call failed. Absent on success.
shownNoRows returned inline.
noticeNoGuidance for this result: empty-result hints, year clamps, where the full set was staged, or how to narrow.
datasetNoPresent when the full result was staged as a dataframe; read its columns with unhcr_dataframe_describe, then query it with unhcr_dataframe_query.
measureNostock: people in a situation on 31 December; flow: events during the year.
completeNoFalse when the server row cap stopped the upstream fetch; the notice says how many upstream rows were fetched and how to narrow.
footnotesNoUNHCR caveats matching rows of the full result, country-specific first; at most 20.
truncatedNoTrue when rows were cut at limit.
data_notesNoHow to read the counts: stock or flow, rounding, the meaning of null, caveats.
total_rowsNoRows in the full result before the inline cut. When complete is false, the result is built from only the upstream rows fetched before the cap, so rows and summed counts can fall short of the complete result.
attributionNoAttribution UNHCR requires when these figures are reused.
latest_yearNoNewest year this dataset publishes.
applied_scopeNoThe scope actually sent upstream, including clamped years and code rewrites.
footnotes_totalNoCaveats matching the full result, before the cap.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / limit / description
      Previous value: -"Rows returned inline, 1–500 (default 100). Sorting runs over the full result first; a larger result is staged as a dataframe where dataframes are enabled."New value: +"Requested inline rows, 1–1000000 (default 100); values above 500 are clamped to 500 with disclosure. Sorting runs over the full result first; a larger result is staged as a dataframe where dataframes are enabled."
    • changedInput schema / properties / limit / maximum
      Previous value: -500New value: +1000000
  2. First observed

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish readOnly/idempotent/openWorld, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: the coverage window (1959 to latest), the per-column meaning of the asylum dimension, and the critical null-vs-zero semantics. It does not mention pagination/clamping or rate limits, but the important semantic traps are disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, no filler; the scope and the four measures are front-loaded, followed by the two highest-risk clarifications (asylum column semantics, null vs zero). Every sentence carries information an agent would otherwise have to guess.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema, 100% parameter coverage, and read-only annotations, the description only needs to resolve domain traps — and it does: the per-column asylum semantics and null-not-zero convention are the two most likely sources of misinterpretation. Nothing essential for correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3, but the description adds real meaning by explaining that 'asylum country' denotes a different country per measure (returned-from, resettlement destination, naturalising country, IDP return on origin) — a semantic distinction the schema only partially implies. It does not elaborate on expand/sort_by/stage behavior, which stays in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Get durable solutions per year ... by country of origin and/or asylum') and enumerates the four measure columns (returned refugees, resettlement, naturalisation, returned IDPs), which implicitly but clearly separates it from siblings like unhcr_get_population, unhcr_get_asylum_applications, and unhcr_get_demographics. An agent can tell what data this returns without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description never states when to choose this tool over alternatives or what conditions make it the right call. Routing hints (resolve names via unhcr_list_reference, join via unhcr_dataframe_query) exist only in the parameter schema, not the description, so the description itself offers no usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.