IMF — International Monetary Fund Data

The International Monetary Fund's macro database. Country-level GDP, inflation, current account, fiscal balance, exchange rates, debt, employment, demographics — across 190+ member countries. The standard cross-country macro source. Free, no auth.

Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.

Why this matters for AI agents

For cross-country macro analysis, the IMF's databases (WEO — World Economic Outlook; IFS — International Financial Statistics; BOP — Balance of Payments) are the canonical source. Where FRED is US-focused, IMF is global and harmonized. Where World Bank focuses on development, IMF focuses on macro/fiscal/financial.

Common flows:

• Country macro snapshot. GDP, inflation, current account for a given country.
• Cross-country comparison. Pull the same indicator across multiple countries to compare.
• Time-series analysis. Historical data for trend analysis.

Used by the trade_country_profile compound and pairs well with Comtrade (trade flows) and BLS (US labor).

Auth

None. IMF Data API is fully public, free.

Major databases

Common pitfalls

• Country code variants. IMF uses ISO 3-letter codes (USA, GBR, DEU). Comtrade uses 3-digit numeric. Census uses 2-letter. Cross-source linking needs translation.
• WEO publishes twice yearly. April and October. Forecasts can shift dramatically between releases — always cite the vintage (e.g., "WEO October 2024").
• Exchange-rate definitions vary. Period average vs. end-of-period vs. PPP vs. real effective. IMF data has all four; specify which.
• Coverage gaps. Small economies and politically isolated countries (North Korea, Venezuela, Eritrea) have spotty data. The IMF API returns nulls; don't treat null as zero.
• Real vs. nominal. Default GDP is nominal in current-USD. For comparisons over time or across rapid-inflation economies, you usually want real (inflation-adjusted, in constant prices) or PPP-adjusted.
• Lag. Annual data published with 6–18 month lag depending on country reporting. Quarterly data faster, ~2–3 month lag for major economies.

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/imf/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 1476+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

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 Imf data" })

The gateway picks the right tool and fills the arguments automatically.

More

• Docs and guides
• pipeworx.io

License

MIT