[Integrations](https://spiral.ai/integrations) › [Gemini CLI](https://spiral.ai/integrations/gemini-cli) › [Eurostat dataset metadata](https://spiral.ai/integrations/gemini-cli/eurostat-dataset-metadata)

# How to Use Eurostat dataset metadata in Gemini CLI

Returns a dataset’s metadata card, dimensions, and code labels. Use it to identify the countries, units, and categories a dataset contains before requesting observations.

|  |  |
| --- | --- |
| Model | Eurostat dataset metadata |
| 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 Eurostat dataset metadata in Gemini CLI

- Use Eurostat dataset metadata to inspect prc_ppp_ind_1 and document the dimensions and labels needed for a Germany–France consumption price comparison.
- Use Eurostat dataset metadata to look this up and give me the result as a table. Save the result in ./assets.
- Pull the latest numbers from Eurostat dataset metadata and tell me what changed since last week.
- Check Eurostat dataset metadata and summarize what you find in three bullet points.
- Pull the newest data from Eurostat dataset metadata and give me the result as a table.

## How to set up Eurostat dataset metadata in Gemini CLI

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

### Use Spiral's MCP server

1. **Add the server**: Or add it to `~/.gemini/settings.json` yourself:

```bash
gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
```

2. **Sign in**: Start `gemini` and run:

```text
/mcp auth spiral
```

3. **Check it**: In Gemini CLI, run `/mcp`. From your shell:

```bash
gemini mcp list
```

### Use the Spiral skill

1. **Send Gemini CLI 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 Eurostat dataset metadata**: 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": "ec-europa-eu/indicators/get_dataset",
    "input": {
      "code": "<code>"
    }
  }'
```

Then paste one of the prompts above: Gemini CLI finds Eurostat dataset metadata on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/gemini-cli

## Eurostat dataset metadata tools and prices

- [Eurostat (ec.europa.eu) · Get dataset](https://spiral.ai/tools/alexandria/ec-europa-eu/indicators/get_dataset) (Alexandria): $0.00873 per call.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| lang | en, fr, de | en | lang |
| max_codes | 1 to 5000 | 200 | Cap on codes listed per dimension; codes_truncated says when a dimension has more. |

## What can you do with Eurostat dataset metadata in Gemini CLI?

Build a European comparison table that keeps country price indices and city purchasing power parities on clearly labeled scales. A coding agent can inspect Eurostat’s dimensions and turn selected observations into charts in your project.

### Prepare an office location comparison

Build a brief for Berlin, Paris, and Madrid with national consumption price levels and separate city purchasing power comparisons. Identify the series and check their units before presenting the results.

### Write a relocation planning brief

Compare France, Germany, and Spain at the country level, then add Paris, Berlin, and Madrid using the EU officials’ city consumption basket. Explain the different populations and reference scales.

### Compare procurement categories across countries

Find the relevant price comparison series and compare food and non-alcoholic beverage indices for Germany, France, and Poland. Use published category averages as context for supplier research.

### Examine the effect of excluding rents

Compare Berlin and Paris purchasing power parities with rents included and excluded for the same half-year. Show how the published comparison changes when housing costs are treated differently.

### Check a European cost comparison before publication

Locate the cited series, inspect its definitions, and retrieve the relevant country or city observations. Check that the article distinguishes Brussels=1 city parities from EU27=100 country indices.

### Build a statistics teaching example

Use France and Germany, plus Paris and Berlin, to demonstrate dataset discovery, statistical dimensions, and reference scales. Have students explain why country price indices and city purchasing power parities answer different questions.

## Overview

- [Alexandria](https://spiral.ai/providers/alexandria)
- [All Gemini CLI guides](https://spiral.ai/integrations/gemini-cli)

## Eurostat dataset metadata in other agents

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

## More Gemini CLI guides

- [Eurostat country price level indices](https://spiral.ai/integrations/gemini-cli/eurostat-country-price-level-indices)
- [Eurostat dataset observations](https://spiral.ai/integrations/gemini-cli/eurostat-dataset-observations)
- [Eurostat city purchasing power parities](https://spiral.ai/integrations/gemini-cli/eurostat-city-purchasing-power-parities)
- [Eurostat dataset search](https://spiral.ai/integrations/gemini-cli/eurostat-dataset-search)
- [EODHD ticker lookup](https://spiral.ai/integrations/gemini-cli/eodhd-ticker-lookup)
- [FCA cryptoasset register](https://spiral.ai/integrations/gemini-cli/fca-cryptoasset-register)

## Questions about Eurostat dataset metadata in Gemini CLI

**Can Gemini CLI use Eurostat dataset metadata?**

Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run Eurostat dataset metadata like any built-in tool.

**How much does Eurostat dataset metadata cost in Gemini CLI?**

$0.00873 per call. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini CLI plan is separate.

**Do I need an Alexandria account to use Eurostat dataset metadata in Gemini CLI?**

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

**How long does it take to set up Eurostat dataset metadata in Gemini CLI?**

About two minutes: add the server, then sign in, then check it.

**Does Gemini CLI wait while Eurostat dataset metadata runs?**

Eurostat dataset metadata runs in the background. Gemini CLI starts the run, checks on it and gives you the json when it's ready.

**How often does Eurostat refresh its database?**

Eurostat refreshes datasets at 11:00 and 23:00 CET when new data or structural changes are available. Those refresh times do not mean every statistical series receives new observations twice daily.

**Can I retrieve the figures exactly as originally published?**

Eurostat serves the latest dataset version and does not maintain documented past versions in this database. An older reference year can therefore contain revised observations.

**How far back do detailed purchasing power comparisons go?**

All 64 analytical categories in prc_ppp_ind_1 are available from 2022 for the 36 participating countries. Earlier estimates for 1995–2021 cover GDP and its main components.

**Can I reuse Eurostat data in a commercial report?**

Eurostat generally permits commercial reuse with source acknowledgment, subject to its exceptions. Its notice excludes commercial reuse of data for countries outside the EU, EFTA, and official acceding or candidate countries, including US, Japanese, and Chinese data.

