MCP server exposing 3 tools for imf.
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/imf/mcp
Content-Type: application/json
{"jsonrpc":"2.0","id":1,"method":"tools/list"}
get_datasets — List or search the IMF's datasets — CPI, WEO (World Economic Outlook), BOP (Balance of Payments), IMTS (trade in goods), GFS (government finance), MFS (monetary and financial), FSI (financial soundness), commodity prices and ~200 more. Returns the dataset id to pass to get_data and search_indicators, plus its name and description. Pass `query` to filter by name, e.g. "inflation", "trade", "government".get_data — Fetch an IMF time series. Identify the series by dataset plus a `dimensions` map of named codes, e.g. get_data({dataset:"CPI", dimensions:{COUNTRY:"USA", INDEX_TYPE:"CPI", COICOP_1999:"_T", TYPE_OF_TRANSFORMATION:"IX", FREQUENCY:"M"}, start:"2024-01"}). Dimension names and order differ per dataset — use search_indicators to see what a dataset accepts. Any dimension you omit is left open, returning every code for it. Returns observations as {period, value} plus the dimension values of each series.search_indicators — Discover what a dataset accepts: its dimension names in key order, and the codes available for each, filtered by `query`. Use this before get_data — e.g. search_indicators({dataset:"CPI", query:"united states"}) finds COUNTRY=USA. Without a query it returns the dimension list and a sample of codes.Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/imf/
Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io