# aurora

Aurora gives agents local statistical analysis with 19 methods, cited findings, and measured error rates. Use it when data needs checking instead of guesses.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 6
- Author: FantasyLab-ai
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/FantasyLab-ai/aurora
- Updated: 2026-09-05
- HTML: https://affpapa.org/en/nevibecode/mcp/aurora

## What it does

Aurora adds statistical analysis to an agent through MCP. It covers 19 methods and returns findings with citations plus measured error rates, giving the agent evidence to show alongside its conclusions.

The project is designed to run locally. Aurora works without API keys, cloud access, or telemetry, and data stays on the machine unless a user explicitly shares one finding. MCP connections are listed for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Cline, Zed, and Windsurf (Devin Desktop).

The Claude Code setup runs `uvx aurora-mcp`, so `uvx` is required for that installation route. Tell the agent which data to inspect and what kind of statistical check you need.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add aurora -- uvx aurora-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from aurora-mcp <command>

### Codex

**Platform CLI**
```bash
codex mcp add aurora -- uvx aurora-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from aurora-mcp <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "aurora": {
            "command": "uvx",
            "args": [
                "aurora-mcp"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from aurora-mcp <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "aurora": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "aurora-mcp"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from aurora-mcp <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add aurora uvx aurora-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from aurora-mcp <command>

## When to use it
- inspect a dataset with statistical methods
- return findings backed by citations
- measure analysis error rates
- run data checks locally through an agent

## Example prompts
- Use Aurora to analyze `sales.csv` and return the main statistical findings with citations.
- Check this dataset for unusual values and report the measured error rates for the methods used.
- Compare the analysis of `events.json` and identify which findings have citation support.

## Similar
- [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89609
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89899
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16730
- [PostHog MCP Server](https://affpapa.org/en/nevibecode/mcp/posthog-mcp-server.md) — MCP server · ★ 40459
- [dbx](https://affpapa.org/en/nevibecode/mcp/dbx.md) — MCP server · ★ 27844
- [Metabase](https://affpapa.org/en/nevibecode/mcp/metabase.md) — MCP server · ★ 49863

---
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