[Integrations](https://spiral.ai/integrations) › [ChatGPT](https://spiral.ai/integrations/chatgpt) › [IMF dataset search](https://spiral.ai/integrations/chatgpt/imf-dataset-search)

# How to Use IMF dataset search in ChatGPT

Returns IMF dataflow records for finding economic datasets. Use it to locate the relevant source for inflation, trade, fiscal statistics, or WEO analysis before requesting metadata or observations.

|  |  |
| --- | --- |
| Model | IMF dataset search |
| Available through | Alexandria |
| Category | Finance |
| Price | $0.00873 per call. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with IMF dataset search in ChatGPT

- Use IMF dataset search to find datasets covering inflation in Brazil and Mexico, and explain what each source measures.
- Use IMF dataset search to look this up and give me the result as a table.
- Pull the latest numbers from IMF dataset search and tell me what changed since last week.
- Check IMF dataset search and summarize what you find in three bullet points.
- Pull the newest data from IMF dataset search and give me the result as a table.

## How to set up IMF dataset search in ChatGPT

Pick the way that suits you. Each takes about two minutes.

### Use the ChatGPT connector

1. **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.

```text
https://api.spiral.ai/mcp
```

2. **Click Connect**: ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.

3. **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

1. **Send ChatGPT this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run IMF dataset search**: One request; the result comes back by polling or a webhook.

```bash
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": "data-imf-org/datasets/dataflows",
    "input": {
      "query": "<query>"
    }
  }'
```

Then paste one of the prompts above: ChatGPT finds IMF dataset search on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/chatgpt

## IMF dataset search tools and prices

- [IMF Data · Dataflows](https://spiral.ai/tools/alexandria/data-imf-org/datasets/dataflows) (Alexandria): $0.00873 per call.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| query |  | — | Case-insensitive words that must all appear in the dataflow id, agency, name or description. Empty lists everything. |
| cursor |  | — | next_cursor from the previous page. |
| page_size | 1 to 1000 | 100 | page_size |

## What can you do with IMF dataset search in ChatGPT?

Prepare a sourced economic comparison of Brazil and Mexico using IMF definitions and figures. A chat app can find suitable datasets, explain their metadata, and present historical observations or WEO projections in a readable table.

### Country growth comparison

Find the relevant IMF datasets, inspect their series definitions, and compare annual growth figures for the United States, Germany, and Japan. Add WEO projections from a single edition to extend the comparison.

### Inflation research brief

Identify IMF inflation datasets and their available series, retrieve historical observations, and add WEO inflation projections for Brazil and Mexico. Label the historical measures and projected measures separately.

### Fiscal comparison for a budget review

Locate fiscal datasets and inspect definitions before comparing government indicators for France, Italy, and Spain. Retrieve historical values and WEO projections for the measures available across all three countries.

### External balance briefing

Find balance-of-payments datasets, check current-account series definitions, and retrieve historical observations for India and Indonesia. Add WEO current-account projections to show the outlook alongside the history.

### Dataset coverage assessment

Search IMF sources for a proposed comparison of Canada, Australia, and Japan. Inspect their dimensions and available series, then retrieve sample observations to establish which comparisons the data supports.

### WEO forecast revision review

Locate WEO releases, inspect indicator definitions, and compare US and German growth projections between the April 2025 and October 2025 editions. Show the change for the same forecast year.

## Overview

- [Alexandria](https://spiral.ai/providers/alexandria)
- [All ChatGPT guides](https://spiral.ai/integrations/chatgpt)

## IMF dataset search in other agents

- [Amp](https://spiral.ai/integrations/amp/imf-dataset-search)
- [Claude](https://spiral.ai/integrations/claude-desktop/imf-dataset-search)
- [Claude Code](https://spiral.ai/integrations/claude-code/imf-dataset-search)
- [Cline](https://spiral.ai/integrations/cline/imf-dataset-search)
- [Codex](https://spiral.ai/integrations/codex/imf-dataset-search)
- [Cursor](https://spiral.ai/integrations/cursor/imf-dataset-search)
- [Devin](https://spiral.ai/integrations/devin/imf-dataset-search)
- [dots](https://spiral.ai/integrations/dots/imf-dataset-search)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/imf-dataset-search)
- [Gemini](https://spiral.ai/integrations/gemini/imf-dataset-search)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/imf-dataset-search)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/imf-dataset-search)
- [goose](https://spiral.ai/integrations/goose/imf-dataset-search)
- [Grok](https://spiral.ai/integrations/grok/imf-dataset-search)
- [Grok Build](https://spiral.ai/integrations/grok-build/imf-dataset-search)
- [Hermes](https://spiral.ai/integrations/hermes/imf-dataset-search)
- [Instinct](https://spiral.ai/integrations/instinct/imf-dataset-search)
- [Manus](https://spiral.ai/integrations/manus/imf-dataset-search)
- [Muse](https://spiral.ai/integrations/muse/imf-dataset-search)
- [Muse Code](https://spiral.ai/integrations/muse-code/imf-dataset-search)
- [n8n](https://spiral.ai/integrations/n8n/imf-dataset-search)
- [Notion](https://spiral.ai/integrations/notion/imf-dataset-search)
- [OpenClaw](https://spiral.ai/integrations/openclaw/imf-dataset-search)
- [opencode](https://spiral.ai/integrations/opencode/imf-dataset-search)
- [Perplexity](https://spiral.ai/integrations/perplexity/imf-dataset-search)
- [Raycast](https://spiral.ai/integrations/raycast/imf-dataset-search)
- [VS Code](https://spiral.ai/integrations/vscode/imf-dataset-search)
- [Windsurf](https://spiral.ai/integrations/windsurf/imf-dataset-search)
- [Zapier](https://spiral.ai/integrations/zapier/imf-dataset-search)

## More ChatGPT guides

- [IMF World Economic Outlook forecasts](https://spiral.ai/integrations/chatgpt/imf-world-economic-outlook-forecasts)
- [IMF dataset structure](https://spiral.ai/integrations/chatgpt/imf-dataset-structure)
- [IBGE statistical table search](https://spiral.ai/integrations/chatgpt/ibge-statistical-table-search)
- [IMF economic observations](https://spiral.ai/integrations/chatgpt/imf-economic-observations)
- [IBGE statistical table metadata](https://spiral.ai/integrations/chatgpt/ibge-statistical-table-metadata)
- [Japan MOF government bond yields](https://spiral.ai/integrations/chatgpt/japan-mof-government-bond-yields)

## Questions about IMF dataset search in ChatGPT

**Can ChatGPT use IMF dataset search?**

Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run IMF dataset search like any built-in tool.

**How much does IMF dataset search 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 IMF dataset search in ChatGPT?**

No. Spiral runs IMF dataset search on its own Alexandria account. You sign in to Spiral once and never paste a key.

**How long does it take to set up IMF dataset search in ChatGPT?**

About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.

**Does ChatGPT wait while IMF dataset search runs?**

IMF dataset search runs in the background. ChatGPT starts the run, checks on it and gives you the json when it's ready.

**How often does IMF update WEO?**

The full WEO database is published twice a year, in April and October. Use its edition to identify the forecast exercise behind the figures.

**How far back does WEO go, and how far ahead does it forecast?**

WEO history starts in 1980. Many indicators and country groups have five-year forecasts, while some have only two forecast years.

**Does every country have a complete WEO history?**

No. Some countries have incomplete or unavailable observations for certain years, so a country comparison may have gaps even within WEO's coverage period.

**What economic subjects does WEO cover?**

WEO includes national accounts, inflation, unemployment, balance of payments, fiscal indicators, and trade. It provides country figures and country-group aggregates.

**Why can valid IMF codes still return no observations?**

SDMX datasets need not contain every possible combination of dimension codes. Availability constraints identify which combinations are present, so valid country and indicator codes alone do not establish coverage.

