MCP server exposing 3 tools for unicef.
This URL is a JSON-RPC 2.0 endpoint over HTTP. Issue POST requests with a JSON-RPC body. Browsers and search crawlers land here on GET.
POST https://gateway.pipeworx.io/unicef/mcp
Content-Type: application/json
{"jsonrpc":"2.0","id":1,"method":"tools/list"}list_dataflows — Browse 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_structure — Get 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_data — Pull 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.Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/unicef/
Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io