unhcr-refugees-mcp-server

UNHCR demographics

unhcr_get_demographics

Read-onlyIdempotent

Get UNHCR year-end stocks (2001 to the latest year) broken down by population type, sex, and age band (0–4, 5–11, 12–17, 18–59, 60+, unknown age), by country of origin and/or asylum. Coverage is partial: each row gives the share of its total that UNHCR could disaggregate by sex, and age bands are null where no breakdown exists. These totals come from a separate collection and need not match unhcr_get_population.

Input Schema

Name	Required	Description	Default
`limit`	No	Inline rows. Default 25; a larger value returns at most 2000 and says so. Sorting runs over the full result first; a larger result is staged as a dataframe where dataframes are enabled.
`stage`	No	Stage 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.
`asylum`	No	Country of asylum — where people sought or hold protection; for returns, the country they returned from — as ISO3 codes (DEU, TUR), case-insensitive, same rules and limit as origin. Omit to sum every asylum country into one row, or set expand to list each.
`expand`	No	List 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
`origin`	No	Country 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 250 distinct codes, enough to list every country in UNHCR's country list. Omit to sum every origin into one row, or set expand to list each.
`sort_by`	No	Order of the full result before the inline cut. year (default) orders by year, then origin ISO3, then asylum ISO3, then population type; total orders largest first, nulls last.	year
`year_to`	No	Last 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_from`	No	First 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.
`population_types`	No	Keep only these population types, case-insensitive: REF refugees, ASY asylum-seekers, OIP other people in need of international protection, IDP internally displaced, STA stateless, OOC others of concern, HST host community, RET returned refugees, RDP returned IDPs. Decode them with unhcr_list_reference (topic population_types). Omit for every type.

Output Schema

Name	Required	Description
`cap`	No	The limit that was applied.
`rows`	No	Inline rows, sorted, up to limit.
`error`	No	Present when the call failed. Absent on success.
`shown`	No	Rows returned inline.
`notice`	No	Guidance for this result: empty-result hints, year and limit clamps, where the full set was staged, or how to narrow.
`dataset`	No	Present when the full result was staged as a dataframe; read its columns with unhcr_dataframe_describe, then query it with unhcr_dataframe_query.
`measure`	No	stock: people in a situation on 31 December; flow: events during the year.
`complete`	No	False when the server row cap stopped the upstream fetch; the notice says how many upstream rows were fetched and how to narrow.
`footnotes`	No	UNHCR caveats matching rows of the full result, at most 20. Caveats on inline rows come before those only on rows past the cut; within each group, country-specific first, then in the order of the first row each matches.
`truncated`	No	True when rows were cut at limit.
`data_notes`	No	How to read the counts: stock or flow, rounding, the meaning of null, caveats.
`total_rows`	No	Rows 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.
`attribution`	No	Attribution UNHCR requires when these figures are reused.
`latest_year`	No	Newest year this dataset publishes.
`applied_scope`	No	The scope actually sent upstream, including clamped years and code rewrites.
`footnotes_total`	No	Caveats matching the full result, before the cap.

Schema Changelog

Changes observed during successful MCP inspections.

Changed12 schema fields changedNov 4, 2026

changedInput schema / properties / asylum / anyOf

Previous value: -[
-  {
-    "description": "One code, or several separated by commas or spaces, e.g. \"SYR\" or \"SYR, AFG\".",
-    "maxLength": 1000,
-    "type": "string"
-  },
-  {
-    "description": "Codes as a list, e.g. [\"SYR\", \"AFG\"]; at most 50.",
-    "items": {
-      "maxLength": 100,
-      "type": "string"
-    },
-    "maxItems": 50,
-    "type": "array"
-  }
-]New value: +[
+  {
+    "description": "One code, or several separated by commas or spaces, e.g. \"SYR\" or \"SYR, AFG\".",
+    "maxLength": 1750,
+    "type": "string"
+  },
+  {
+    "description": "Codes as a list, e.g. [\"SYR\", \"AFG\"].",
+    "items": {
+      "maxLength": 100,
+      "type": "string"
+    },
+    "maxItems": 1000,
+    "type": "array"
+  }
+]

changedInput schema / properties / asylum / description

Previous value: -"Country 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."New value: +"Country of asylum — where people sought or hold protection; for returns, the country they returned from — as ISO3 codes (DEU, TUR), case-insensitive, same rules and limit as origin. Omit to sum every asylum country into one row, or set expand to list each."

changedInput schema / properties / limit / default
```
Previous value: -100New value: +25
```

changedInput schema / properties / limit / description

Previous 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."New value: +"Inline rows. Default 25; a larger value returns at most 2000 and says so. Sorting runs over the full result first; a larger result is staged as a dataframe where dataframes are enabled."

removedInput schema / properties / limit / maximum
```
Removed value: -1000000
```
addedInput schema / properties / limit / multipleOf
```
Added value: +1
```

changedInput schema / properties / origin / anyOf

Previous value: -[
-  {
-    "description": "One code, or several separated by commas or spaces, e.g. \"SYR\" or \"SYR, AFG\".",
-    "maxLength": 1000,
-    "type": "string"
-  },
-  {
-    "description": "Codes as a list, e.g. [\"SYR\", \"AFG\"]; at most 50.",
-    "items": {
-      "maxLength": 100,
-      "type": "string"
-    },
-    "maxItems": 50,
-    "type": "array"
-  }
-]New value: +[
+  {
+    "description": "One code, or several separated by commas or spaces, e.g. \"SYR\" or \"SYR, AFG\".",
+    "maxLength": 1750,
+    "type": "string"
+  },
+  {
+    "description": "Codes as a list, e.g. [\"SYR\", \"AFG\"].",
+    "items": {
+      "maxLength": 100,
+      "type": "string"
+    },
+    "maxItems": 1000,
+    "type": "array"
+  }
+]

changedInput schema / properties / origin / description

Previous value: -"Country 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."New value: +"Country 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 250 distinct codes, enough to list every country in UNHCR's country list. Omit to sum every origin into one row, or set expand to list each."

changedOutput schema / properties / error / properties / data / properties / reason / description

Previous value: -"Machine-readable failure mode. Declared by this tool: `unknown_country_code`: An origin or asylum value is not an ISO3 code in UNHCR's country list (after ISO2 normalization). `invalid_year_window`: year_from is later than year_to. `year_out_of_coverage`: The whole requested window lies outside the dataset's published years. `conflicting_scope`: expand names a dimension that origin or asylum already filters. `upstream_busy`: This server's UNHCR request queue cannot start the call's requests before its deadline, or UNHCR answered 429. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `unknown_country_code`: An origin or asylum value is not an ISO3 code in UNHCR's country list (after ISO2 normalization). `invalid_year_window`: year_from is later than year_to. `year_out_of_coverage`: The whole requested window lies outside the dataset's published years. `conflicting_scope`: expand names a dimension that origin or asylum already filters. `too_many_country_codes`: origin or asylum lists more distinct codes than one filter accepts. `upstream_busy`: This server's UNHCR request queue cannot start the call's requests before its deadline, or UNHCR answered 429. Other values are possible when a failure originates below the handler."

changedOutput schema / properties / error / properties / data / properties / reason / examples

Previous value: -[
-  "unknown_country_code",
-  "invalid_year_window",
-  "year_out_of_coverage",
-  "conflicting_scope",
-  "upstream_busy"
-]New value: +[
+  "unknown_country_code",
+  "invalid_year_window",
+  "year_out_of_coverage",
+  "conflicting_scope",
+  "too_many_country_codes",
+  "upstream_busy"
+]

changedOutput schema / properties / footnotes / description

Previous value: -"UNHCR caveats matching rows of the full result, country-specific first; at most 20."New value: +"UNHCR caveats matching rows of the full result, at most 20. Caveats on inline rows come before those only on rows past the cut; within each group, country-specific first, then in the order of the first row each matches."

changedOutput schema / properties / notice / description

Previous value: -"Guidance for this result: empty-result hints, year clamps, where the full set was staged, or how to narrow."New value: +"Guidance for this result: empty-result hints, year and limit clamps, where the full set was staged, or how to narrow."

Changed2 schema fields changedOct 20, 2026

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
```

First observedOct 4, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Beyond the read-only, open-world, and idempotent annotations, it discloses important data behavior: coverage begins in 2001, disaggregation is partial, sex coverage is reported per row, and unavailable age breakdowns are null. The warning about a separate collection and possible total mismatches helps prevent incorrect reconciliation with sibling results.

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 move from purpose and scope to coverage limitations and then the sibling-data caveat, with the core operation front-loaded. The age-band list and both caveats earn their space, and there is no filler or repeated schema detail.

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?

For a complex nine-parameter read tool, the description covers the essential dataset scope and the pitfalls most likely to cause misinterpretation. The exhaustive input schema handles invocation details, annotations cover operational safety, and the output schema removes the need to enumerate return fields.

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

Parameters3/5

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

Schema description coverage is 100%, and the schema already documents filters, expansion, sorting, staging, limits, defaults, and code formats in detail. The description supplies useful dataset-level context but adds little parameter-specific meaning such as syntax or interaction rules, so the high-coverage baseline applies.

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?

“Get UNHCR year-end stocks” gives a specific verb and resource, while the year range, demographic breakdowns, and origin/asylum dimensions define its scope precisely. Naming unhcr_get_population and warning that totals may differ also distinguishes it from the closest sibling.

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

Usage Guidelines4/5

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

The description makes the appropriate context clear: this tool provides sex- and age-disaggregated year-end stocks and should not be treated as interchangeable with unhcr_get_population. It stops short of an explicit when-not rule or directing agents to a sibling for particular alternative needs.

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

All unhcr-refugees-mcp-server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.