How to Use OECD dataset catalog in ChatGPT
Returns OECD dataset names and references. Use it to find the right statistical dataset before inspecting its definitions or fetching observations.
Prompts to try with OECD dataset catalog in ChatGPT
Copy an example into ChatGPT, or ask in your own words.
Use OECD dataset catalog to find datasets about social expenditure that could support a comparison of Sweden and Canada.
Use OECD dataset catalog to look this up and give me the result as a table.
Pull the latest numbers from OECD dataset catalog and tell me what changed since last week.
Check OECD dataset catalog and summarize what you find in three bullet points.
Pull the newest data from OECD dataset catalog and give me the result as a table.
How to set up OECD dataset catalog in ChatGPT
Pick the way that suits you. Each takes about two minutes.
Use the ChatGPT connector
- Add a custom MCP server
In ChatGPT open Plugins, then Add › Add custom MCP server. Name it Spiral, paste this URL and keep Authentication on OAuth. Tick I understand and want to continue, then click Create.
https://api.spiral.ai/mcp
- Click Connect
ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.
- Sign in to Spiral and approve
Sign in, pick the organization ChatGPT should use and click Authorize. Spiral gives the connection its own API key; ChatGPT never sees it, and you can remove the connection under Settings › Connected apps.
Use the Spiral skill
- Send ChatGPT this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run OECD dataset catalog
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "alexandria", "model": "sdmx-oecd-org/datasets/dataflows_list", "input": { "q": "<q>" } }'
Then paste one of the prompts above: ChatGPT finds OECD dataset catalog on Spiral, shows the price and runs it.
OECD dataset catalog providers and prices
Spiral runs OECD dataset catalog through Alexandria. Open a card for today's price, with every fee included.
Settings you can ask for
Ask ChatGPT for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Page size | 1 to 500 | 100 | page_size |
Every API field of OECD Data Explorer SDMX API · Dataflows list is on its tool page: open its card above.
What can you do with OECD dataset catalog in ChatGPT?
Prepare an OECD country comparison that explains what the selected statistics measure. A chat app can find relevant datasets, explain their classifications, and use available observations to answer a focused economic or policy question.
Compare tax revenue across countries
Prepare a Canada, France, and Germany comparison: find the relevant dataset, inspect its dimensions, decode classifications, and retrieve matching observations. Check update status before refreshing the comparison and recheck individual figures selected for the report.
Maintain a trade briefing
Build a recurring United States and Japan trade briefing. Locate the dataset, check its definitions and classifications, retrieve comparable periods, inspect update status on later runs, and verify the observations quoted in the briefing.
Review social expenditure trends
Prepare a Sweden and Canada social expenditure comparison. Find the dataset, inspect available measures, explain classification labels, retrieve matching observations, check for updates, and recheck the figures used in the final table.
Refresh the evidence behind a policy report
Revisit OECD evidence used in a report on Australia and New Zealand. Confirm the dataset reference and structure, resolve classification labels, check update status, refresh the selected observations, and verify each headline figure individually.
Check coverage before commissioning an analysis
Find candidate OECD datasets for a Mexico, Brazil, and Chile comparison. Inspect their structures and available codes to determine which requested measures can support the comparison.
More on OECD dataset catalog and ChatGPT
Overview
OECD dataset catalog in other agents
Questions about OECD dataset catalog in ChatGPT
Can ChatGPT use OECD dataset catalog?
Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run OECD dataset catalog like any built-in tool.
How much does OECD dataset catalog cost in ChatGPT?
$0.00873 per call. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your ChatGPT plan is separate.
Do I need an Alexandria account to use OECD dataset catalog in ChatGPT?
No. Spiral runs OECD dataset catalog on its own Alexandria account. You sign in to Spiral once and never paste a key.
How long does it take to set up OECD dataset catalog in ChatGPT?
About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.
Does ChatGPT wait while OECD dataset catalog runs?
OECD dataset catalog runs in the background. ChatGPT starts the run, checks on it and gives you the json when it's ready.
Does OECD data cover every country?
Coverage includes OECD countries and selected economies outside the OECD. Availability also depends on the dataset and the particular country, measure, and period combination.
How often does OECD data change?
Many datasets update annually, some monthly, and a few short-term economic datasets daily. OECD does not apply one update schedule to all its statistics.
Why can an OECD country or measure have no results?
OECD may have no observations for the selected combination of country, measure, and period. A country appearing elsewhere in the source does not establish coverage for that combination.
What download limit does OECD impose?
OECD currently permits 60 data downloads per hour and temporarily blocks requests above that limit. The restriction also covers CSV downloads from its browser interface.
Can an OECD dataset change its structure?
Yes. New dataflow versions can add, remove, or rename dimensions, so an older selection can require changes before it works with the new structure.
Start using OECD dataset catalog in ChatGPT
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into ChatGPT:
set up https://spiral.ai/SKILL.md


