# autario

autario connects services and public datasets to an AI assistant through MCP. Use it to ask about ads, sales, analytics, and finance data.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · 5089 installs
- Author: autario
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://smithery.ai/server/autario/data
- Updated: 2026-04-05
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/autario

## What it does

autario gives an assistant one data layer for connected services and public datasets. It can read advertising accounts, shop orders, analytics, search, social, CRM, and finance data. Supported services named in the project include Shopify, Meta Ads, Google Analytics, Search Console, LinkedIn, and Stripe.

The server can search and query datasets from World Bank, IMF, Eurostat, OECD, WHO, and FRED. It also runs correlation, regression, driver, and seasonality analysis on the server, then supports charts and data apps built from the results.

Service connectors are read-only. Your own data requires OAuth sign-in or an API key, while public datasets need no setup.

## Requirements
- Remote server: `https://data--autario.run.tools`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http data https://data--autario.run.tools
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add autario --url https://data--autario.run.tools
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "autario": {
            "url": "https://data--autario.run.tools"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "autario": {
            "type": "http",
            "url": "https://data--autario.run.tools"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http autario https://data--autario.run.tools
```

## When to use it
- match Meta Ads spend with purchases
- find a public dataset about a topic
- compare indicators across countries
- test data for correlation or seasonality
- read numbers from a connected service

## Example prompts
- Find World Bank datasets about unemployment and compare several countries.
- Check my analytics data for seasonality and identify the main drivers.

## Similar
- [claude-ecom](https://affpapa.org/en/nevibecode/plugins/claude-ecom.md) — plugin · ★ 1013 repo stars
- [hypequery ClickHouse](https://affpapa.org/en/nevibecode/mcp/hypequery-clickhouse.md) — MCP server · ★ 106 repo stars
- [data-pipeline](https://affpapa.org/en/nevibecode/skills/data-pipeline.md) — skill · 5100 installs
- [ETL Pipeline](https://affpapa.org/en/nevibecode/skills/etl-pipeline.md) — skill · 4900 installs
- [data-analyst](https://affpapa.org/en/nevibecode/skills/data-analyst.md) — skill · 2700 installs
- [tinybird-cli-guidelines](https://affpapa.org/en/nevibecode/skills/tinybird-cli-guidelines.md) — skill · 1300 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
