mcpField
U
Unhcr

Unhcr

Remote
pipeworx.ioLegal & Government0Updated 5w ago

About Unhcr

Unhcr is an MCP server for UNHCR refugee data. It serves users analyzing forcibly displaced and stateless populations, asylum applications, and decisions, with country-code lookup and filters for origin and asylum countries.

Key features

  1. 01Query displaced and stateless population data
  2. 02Retrieve asylum application statistics
  3. 03Retrieve asylum decision outcomes
  4. 04List UNHCR country codes

Use cases

  1. 01Analyze refugee populations by year and country
  2. 02Compare asylum applications by origin and asylum country
  3. 03Review categories of asylum decisions

MCP support

It exposes tools for population data, asylum applications, asylum decisions, and country references to MCP clients. It connects through Pipeworx or runs as a local stdio MCP server.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gateway.pipeworx.io/unhcr/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

mcp-unhcr

UNHCR Refugee Data Finder MCP (keyless).

Part of Pipeworx — an MCP gateway connecting AI agents to 1684+ live data sources.

Tools

ToolDescription
populationForcibly displaced & stateless persons by year and country: refugees, asylum_seekers, idps (internally displaced), returned_refugees, returned_idps, stateless, others. Filter by coo (country of origin) and/or coa (country of asylum). coo_all/coa_all=true breaks the totals DOWN by that dimension (one row per origin or asylum country). NOTE: coo/coa take UNHCR's 3-letter code (e.g. Germany='GFR', not ISO3 'DEU') — resolve with list_countries first.
asylum_applicationsAsylum applications lodged, by year, country of origin (coo) and country of asylum (coa). Rows carry procedure_type, app_type, dec_level and the applied count; response.total.applied is the aggregate. coo/coa take UNHCR 3-letter codes (see list_countries).
asylum_decisionsDecisions on asylum claims, by year, country of origin (coo) and country of asylum (coa). Each row breaks out dec_recognized, dec_other, dec_rejected, dec_closed and dec_total; response.total aggregates the same fields. coo/coa take UNHCR 3-letter codes (see list_countries).
list_countriesReference list of countries/territories UNHCR tracks. Use this to map a country name to the code you pass as coo/coa in the other tools. Each item has: code (UNHCR 3-letter, USE THIS for filtering), iso (true ISO3), iso2, name, region, majorArea. Paginated — large list, raise limit or page through (response.maxPages).

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "unhcr": {
      "url": "https://gateway.pipeworx.io/unhcr/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/unhcr/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1684+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/population \
  -H 'Content-Type: application/json' \
  -d '{"yearFrom":2019,"yearTo":2023}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/population. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "unhcr": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-unhcr"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-unhcr

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Unhcr data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.