Connect IMF Data to ChatGPT
Query IMF Data directly from ChatGPT. Arlet links the two through one MCP connection and takes care of API keys.
Connects your AI client to IMF Data via the SDMX 3.0 API (api.imf.org). The legacy SDMX 2.0 endpoints (dataservices.imf.org) are retired, and old IFS-style series codes do not carry over — find the current dataflow first.
Tools:
- search_imf_dataflows: keyword search over all dataflows (list cached in the runtime).
- get_imf_dataflow_dimensions: dimension order and codes for one dataflow; shows the exact key template for the data query.
- get_imf_data: observations for a dimension key like 'USA.CPI.CP01.IX.A' ('*' = wildcard), with lastNObservations control.
Attribution: data are from IMF Data (https://data.imf.org). Responses carry the source name.
How to connect IMF Data to ChatGPT
- 1
In the Arlet dashboard, open Data tools, find IMF Data and switch it on. No API key setup is needed.
- 2
In ChatGPT, open Settings → Plugins → Browse plugins and click + at the top right.
- 3
In the New Plugin form, enter "Arlet" as the Name, choose Server URL for Connection and enter https://mcp.arlet.dev/mcp/, pick OAuth for Authentication, check the risk acknowledgement and click Create.
- 4
Open the Arlet plugin you created, click Sign in with Arlet, sign in with Google and click Allow. The connection is complete.
If the Plugins screen is not shown, turn on Developer mode under Settings → Security and login.