get_data

Pack: unicef · Endpoint: https://gateway.pipeworx.io/unicef/mcp

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.

Parameters

NameTypeRequiredDescription
dataflow_idstringyesUNICEF dataflow id, e.g. “CME”. The agency,flow,version reference is built automatically.
keystringnoDot-separated dimension filter (one position per dimension, empty = wildcard), e.g. ”.CME_MRY0T4..”. Omit for all series.
start_periodstringnoStart period, e.g. “2010”.
end_periodstringnoEnd period, e.g. “2022”.
last_nnumbernoReturn only the last N observations per series.
max_seriesnumbernoCap the number of decoded series returned (default 200).

Example call

curl -X POST https://gateway.pipeworx.io/unicef/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"get_data","arguments":{}}}'

Connect

Add this to your MCP client config, or use one-click install buttons:

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

See Getting Started for client-specific install steps.

Regenerated from source · build June 2, 2026