Aurora

Overview

Aurora is a Model Context Protocol (MCP) server: Glass-box statistical analysis for agents: 19 methods, cited findings, measured error rates. In practice that means any MCP-compatible AI assistant can call Aurora's tools directly — the model decides when to use them in a conversation or agent run.

It runs locally: the Python package aurora-mcp (via uvx) speaks MCP over stdio on your machine. No credentials are required — it works out of the box. The current release is v0.10.0, published under the Apache-2.0 license, with source at FantasyLab-ai/aurora on GitHub.

Aurora is listed under AI & Agents on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Aurora for FantasyLab-ai, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "aurora": {
      "command": "uvx",
      "args": [
        "aurora-mcp"
      ]
    }
  }
}