autario-mcp

# autario-mcp

**Verified data for AI agents.** 2,700+ public datasets (World Bank, FRED, Eurostat, OECD, WHO, ECB, US Census, IMF) joined under one ontology, with built-in statistical analysis and chart publishing. Plug it into Claude Desktop, ChatGPT, Cursor, or any MCP-compatible client | your model gets numbers it cannot hallucinate.

[autario.com](https://autario.com/?utm_source=mcp_readme&utm_medium=hero&utm_campaign=marketplace) | [Documentation](https://autario.com/documentation?utm_source=mcp_readme&utm_medium=hero&utm_campaign=marketplace#api-mcp) | [Get an API Key](https://autario.com/account?utm_source=mcp_readme&utm_medium=hero&utm_campaign=marketplace&tab=apikeys)

## Why autario-mcp

- **No hallucinated numbers.** Every value is sourced from a known publisher and cited back to a primary URL. Use `verify_value` to double-check any claim.
- **Cross-dataset joins, no setup.** Indicators across different datasets share `autario_time` + `autario_entity` shadow columns, so `get_entity_data(USA, [gdp, unemployment, life_expectancy])` returns one wide table, joined automatically.
- **Statistical primitives built-in.** `correlate`, `regression`, `find_drivers`, `lag_analysis`, `seasonality_decomposition` and more, with effect sizes, p-values, and plain-language interpretations.
- **Charts that persist.** `publish_chart` writes a Plotly spec to autario.com. The result is a permanent, embeddable URL like `autario.com/chart/{slug}` | the LLM builds the spec, autario pulls real rows for it, no hallucinated data path.
- **LLM-agnostic.** Works with Claude, GPT, Gemini, local models | anything that speaks MCP.

## Quick Demo

Install the server, then ask your assistant questions like these. The model picks the right tools and answers with cited data.

```text
Ask:    "What drives US inflation? Look at money supply, oil prices, and unemployment."
Tools:  list_indicators -> find_drivers
Output: Ranked drivers with r, p-value, R squared per candidate.
```

```text
Ask:    "Compare life expectancy in Germany, USA and Japan from 2000 to 2023, then publish a chart."
Tools:  compare_entities -> publish_chart
Output: Wide-format table joined on year, plus a permanent autario.com/chart/{slug} URL.
```

```text
Ask:    "Is consumer confidence a leading indicator of US retail sales?"
Tools:  lag_analysis
Output: Cross-correlation peak at lag k, with interpretation in months.
```

## Install

### Claude Desktop, Cursor, Cline (stdio)

`~/.config/claude/claude_desktop_config.json` on Mac/Linux, `%APPDATA%\Claude\claude_desktop_config.json` on Windows.

```json
{
  "mcpServers": {
    "autario": {
      "command": "npx",
      "args": ["autario-mcp"]
    }
  }
}
```

Restart your client. The server reports tool count to stderr on launch.

### Claude Web, OpenAI Custom GPTs, any HTTP MCP client

Point your client at the hosted endpoint. No install needed.

```text
URL:        https://autario.com/mcp
Transport:  Streamable HTTP (POST /mcp)
```

The hosted endpoint also supports MCP prompts: `analyze-dataset`, `create-chart`, `compare-countries`.

### Enable write tools (publish charts, create datasets)

Add API credentials to the stdio config or send them as `x-api-key` / `x-api-secret` headers to the HTTP endpoint.

```json
{
  "mcpServers": {
    "autario": {
      "command": "npx",
      "args": ["autario-mcp"],
      "env": {
        "AUTARIO_API_KEY":    "your_key",
        "AUTARIO_API_SECRET": "your_secret"
      }
    }
  }
}
```

Get keys at [autario.com/account](https://autario.com/account?utm_source=mcp_readme&utm_medium=install&utm_campaign=marketplace&tab=apikeys).

## Tool Reference

<!-- TOOLS:START -->
<!-- generated by scripts/check-readme-sync.js | do not edit manually | run `npm run build-readme` after changing tools.js -->

_28 MCP tools, organized by function._

### Discovery & Query

Search the catalog, inspect schemas, pull rows.

| Tool | What it does | Parameters |
| --- | --- | --- |
| `search_datasets` | Search the Autario public data catalog. Returns dataset IDs, titles, descriptions, categories, publishers, row counts, last_refreshed_at, AND trusted ontology fields (topic, subtopic, unit, frequen... | query (string), category (string), limit (number), page (number) |
| `list_indicators` | Browse the Autario indicator registry — semantic layer over all 2600+ datasets. Each indicator has a topic (economy, health, energy, …), unit (USD, %, years, …), frequency (year/month/day), and ent... | topic (string), unit (string), frequency (string), entity_type (string), publisher (string), search (string), limit (number) |
| `get_entity_profile` | Get all indicators available for one entity (country, aggregate, etc.). Returns indicator IDs with metadata + time coverage. Use this to discover what you can query about Germany, USA, G7, or any k... | **entity_id** (string), topic (string) |
| `get_dataset_info` | Get full metadata for a specific dataset including title, description, publisher, category, keywords, row count, and creation date. | **dataset_id** (string) |
| `get_dataset_schema` | Get the column names, data types, and total row count for a dataset. Always call this before query_dataset to understand the available columns for filtering and sorting. | **dataset_id** (string) |
| `query_dataset` | Query data from a dataset with optional filtering, sorting, and field selection. Supports server-side aggregations (avg/sum/count/min/max/stddev/median) with optional GROUP BY for token-efficient q... | **dataset_id** (string), limit (number), offset (number), fields (string), sort (string), filter (array), aggregate (string), groupby (string) |
| `list_charts` | List published chart visualizations on Autario. Returns chart IDs, titles, insights, linked datasets, and creation dates. Use to discover existing analyses. | q (string), limit (number), offset (number) |
| `get_chart` | Get a specific chart by ID or slug. Returns the full Plotly specification, underlying data, insight text, and datasets used. The chart URL is shareable at autario.com/chart/{id}. | **chart_id** (string) |

### Cross-Dataset Joins (Ontology)

The differentiator. Join indicators across datasets via shared time + entity shadow columns. No manual relationship setup.

| Tool | What it does | Parameters |
| --- | --- | --- |
| `get_entity_data` | Fetch wide-format data for ONE entity across MULTIPLE indicators — joined automatically on time via shadow columns. This is the "cross-dataset join" capability: no manual relationship setup needed.... | **entity_id** (string), **indicators** (array), time (string) |
| `compare_entities` | Compare ONE indicator across MULTIPLE entities (e.g. GDP of DEU vs USA vs CHN). Returns wide-format rows like [{time:"2020", DEU:3846, USA:20937, CHN:14688}, …]. Use this for country comparisons, c... | **entities** (array), **indicator** (string), time (string) |
| `verify_value` | Verify that a claimed value is correct. Use this when a user asks "did you hallucinate that?" or when you want to double-check your cited numbers before presenting. Pass the indicator, entity, time... | **indicator** (string), **entity** (string), **time** (string), expected (number) |

### Statistical Analysis

Run analyses against verified data. Outputs include effect sizes, p-values, and plain-language interpretations.

| Tool | What it does | Parameters |
| --- | --- | --- |
| `describe` | Summary statistics for a single indicator+entity: n, mean, median, std, min/max, quartiles, skew, histogram. Use FIRST before running any test so you know what the data looks like (sample size, com... | **indicator** (string), **entity** (string), time (string) |
| `correlate` | Compute Pearson + Spearman correlation between two indicators for one entity. Returns r, p-value, n, and human-readable interpretation. Use for "does X move with Y?" questions. Includes causation d... | **entity** (string), **a** (string), **b** (string), time (string) |
| `regression` | Linear regression of y ~ x for one entity. Returns slope, intercept, R² and interpretation. Use for "how does X predict Y?" questions. | **entity** (string), **y** (string), **x** (string), time (string) |
| `pct_change` | Period-over-period percentage change for an indicator. Use for growth rates (YoY, QoQ, MoM). | **entity** (string), **indicator** (string), time (string), period (string) |
| `rolling_stats` | Rolling window statistics (mean/std/min/max/sum) for an indicator. Smooths noise, reveals trends. | **entity** (string), **indicator** (string), window (number), op (string), time (string) |
| `calculate` | Create a derived series from two indicators using an Excel-style op: ratio (A/B), ratio_pct (A/B*100), diff (A-B), sum (A+B), product (A*B). Returns the per-timepoint result + summary. Use for thin... | **a** (string), **b** (string), **entity** (string), op (string), time (string) |
| `lag_analysis` | Cross-correlation at multiple lags. Answers "does A lead or lag B?". Peak \|r\| at positive lag means A precedes B by that many periods. Common use: "is consumer confidence a leading indicator of ret... | **a** (string), **b** (string), **entity** (string), max_lag (number), time (string) |
| `seasonality_decomposition` | Additive decomposition Y = trend + seasonal + residual. Use this to strip the seasonal cycle from a series and reveal the underlying trend \| great for monthly or quarterly data (retail sales, unemp... | **indicator** (string), **entity** (string), period (number), time (string) |
| `find_drivers` | KILLER ANALYSIS: given a target KPI + multiple candidate indicators, rank which candidates best predict the target by correlation strength. Perfect for "what moves my KPI?" questions. Returns ranke... | **entity** (string), **target_indicator** (string), **candidates** (array), time (string) |
| `what_matters` | HEADLINE OP: given an outcome metric + entity, rank which other metrics best explain the outcome. Auto-selects candidates from the ontology if `candidates