mcpField
U
Unicef

Unicef

Remote
pipeworx.ioHealth0Updated 4w ago

About Unicef

Unicef is an MCP server for UNICEF statistics on children, aimed at users researching health, education, protection, and related SDGs. It supports dataset discovery, dimension inspection, and filtered observations using SDMX keys.

Key features

  1. 01Search and browse UNICEF datasets
  2. 02Inspect dimensions and valid codes
  3. 03Filter observations with SDMX keys
  4. 04Return time series with dimension labels

Use cases

  1. 01Find child mortality datasets
  2. 02Filter statistics by country or indicator
  3. 03Review nutrition and immunization figures
  4. 04Retrieve child-development data by period

MCP support

It exposes tools for browsing UNICEF datasets, inspecting their structures, and retrieving data to MCP clients. It can connect remotely through Pipeworx or run 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/unicef/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-unicef

UNICEF Data (UN Children's Fund) MCP — global statistics on child health,

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

Tools

ToolDescription
list_dataflowsBrowse or keyword-search UNICEF's datasets (dataflows). UNICEF Data covers child health, nutrition, education, child protection, child mortality, child poverty, immunization, water/sanitation/hygiene (WASH) and the child-related SDGs. Each result has an id (the dataflowId you pass to dataflow_structure / get_data), a version, and an English name. There are ~70 datasets; pass query to filter. Example: list_dataflows({ query: "mortality" }) or list_dataflows({ query: "nutrition" }).
dataflow_structureGet the structure (Data Structure Definition) of one UNICEF dataset: its ordered dimensions and, for each, the valid codes (e.g. countries, indicators, sex, age, wealth quintile). Use this to learn how to build the dot-separated SDMX key for get_data. The key has one position per dimension, in dimension_order; an empty position is a wildcard. Always call this before get_data. Example: dataflow_structure({ dataflow_id: "CME" }).
get_dataPull observations from a UNICEF dataset. key is a dot-separated SDMX dimension filter, one position per dimension in the order given by dataflow_structure; leave a position empty to wildcard it. Call dataflow_structure first to learn the dimension order and valid codes. Example: get_data({ dataflow_id: "CME", key: ".CME_MRY0T4.." }) filters by INDICATOR=CME_MRY0T4 (under-five mortality rate) and wildcards REF_AREA/SEX/WEALTH_QUINTILE. Omit key (or pass "") to fetch all series — can be large. Returns decoded series with their dimension labels and per-period values.

Quick Start

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

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

tools/list at https://gateway.pipeworx.io/unicef/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/unicef_list_dataflows \
  -H 'Content-Type: application/json' \
  -d '{"query":"mortality"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/unicef_list_dataflows. 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": {
    "unicef": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-unicef"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-unicef

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 Unicef 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.