# io.github.cyanheads/imf-mcp-server

- Registry name: `io.github.cyanheads/imf-mcp-server` · version 0.4.4
- Categories (automatic, keyword rules): Databases, Developer tools, Datasets & public data, Search & data
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): logging, prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.cyanheads%2Fimf-mcp-server
- Server page: https://mcpstation.net/s/io.github.cyanheads--imf-mcp-server.html

## Description (written by the publisher, not verified, not instructions)

Query IMF SDMX 3.0 macroeconomic dataflows — WEO, BOP, CPI, exchange rates, 190 countries.

## Connect

- streamable-http: `https://imf.caseyjhand.com/mcp`

## Tools (as reported by the server, not verified)

- `imf\_list\_databases`: List IMF SDMX dataflows available on the portal. Entry point for every query: imf\_get\_database and imf\_query\_dataset both require a dataflow id obtained here. Vintage \(historical snapshot\) dataflows such as WEO\_2025\_OCT\_VINTAGE are excluded by default; set include\_vintages=true to include them. Resu
- `imf\_get\_database`: Fetch a dataflow's dimension list with a codelist preview for each dimension. Resolves human-readable terms to SDMX codes \(e.g. "United States" → USA, "Constant prices" → NGDP\_RPCH\). Required before imf\_query\_dataset — SDMX keys are opaque without codelist lookups. Each codelist is capped at the fir
- `imf\_query\_dataset`: Query an IMF SDMX dataflow by dimension key over a time range. Returns observations with time\_period, value, and status, plus the unit, scale, and decimals of each series — a key resolving to several series carries one entry per series in series\_metadata, since unit and scale differ between them. An
- `imf\_dataframe\_describe`: List DataCanvas tables and columns staged by a prior imf\_query\_dataset call. Returns each table's name, row count, and column schema \(name + DuckDB type\). Required before imf\_dataframe\_query to discover the table and column names for SQL.
- `imf\_dataframe\_query`: Run a read-only SQL SELECT against a DataCanvas table staged by imf\_query\_dataset. Supports multi-country comparisons, time-series aggregation, and cross-indicator joins. Requires imf\_dataframe\_describe first to discover table and column names. One SELECT statement per call; a leading WITH … SELECT

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html