Aurora Docs
MCP Server

Aurora MCP Server — Setup & Configuration

Connect Aurora Intelligence to Claude Desktop, ChatGPT, Claude Code, Cursor, and other MCP-compatible clients to query your GEO tracking data conversationally.

What is MCP?

The Model Context Protocol (MCP) is an open standard that lets AI assistants connect to external tools and data sources. Aurora's MCP server lets you query your GEO tracking data directly from your favorite AI client — no dashboards needed.

What You Get

Connect Aurora MCP and your AI assistant can:

  • Check brand visibility — see how often AI platforms mention and cite your brand, with visibility scores
  • Analyze citations — find which URLs and domains AI models recommend for your tracked queries
  • Track keywords — monitor which terms AI providers associate with your brand and competitors
  • Compare providers — see differences across all 7 tracked AI platforms
  • Generate reports — ask for weekly summaries, trend comparisons, or competitive analysis in natural language

Tracked AI Providers

Aurora monitors your brand across these AI platforms:

ProviderType
ChatGPTConversational AI
GeminiConversational AI
PerplexityAI Search
Microsoft CopilotConversational AI
Google AI ModeAI Search
Google AI OverviewSearch Feature
Yandex NeuroAI Search (Russian market)

Prerequisites

  • An active Aurora Intelligence subscription
  • At least one campaign with tracking data
  • An MCP-compatible client (see setup instructions below)

Setup

No API keys needed. Aurora uses OAuth — your browser will open automatically so you can sign in with your Aurora account. No API keys, tokens, or secrets to copy.

Claude Desktop

  1. Open your Claude Desktop config file:

    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Windows: %APPDATA%\Claude\claude_desktop_config.json
  2. Add the Aurora MCP server:

{
  "mcpServers": {
    "aurora": {
      "url": "https://aurora-mcp.stefandukic209.workers.dev/mcp"
    }
  }
}
  1. Restart Claude Desktop (quit and reopen, not just close the window).

  2. The first time you ask Claude to use an Aurora tool (e.g. "List my Aurora campaigns"), a browser window will open automatically where you sign in with your Aurora Intelligence account. After signing in, return to Claude Desktop — it will be connected.

Claude Code (CLI)

  1. Run this command in your terminal:
claude mcp add aurora --transport http https://aurora-mcp.stefandukic209.workers.dev/mcp
  1. Connect via the /mcp command: Type /mcp in Claude Code and select the Aurora server. A browser window will open for you to sign in with your Aurora account.

Important: Don't ask Claude to "connect to Aurora" or "use my API key" — there are no API keys. Just type /mcp, authenticate in the browser, and then ask Claude to use Aurora tools normally (e.g. "List my Aurora campaigns").

ChatGPT

  1. In ChatGPT, go to Settings → Connected Apps.
  2. Click Add MCP Server and enter the URL:
https://aurora-mcp.stefandukic209.workers.dev/mcp
  1. A browser window will open for you to sign in with your Aurora account.

Cursor

  1. Add to your Cursor MCP settings (.cursor/mcp.json in your project root):
{
  "mcpServers": {
    "aurora": {
      "url": "https://aurora-mcp.stefandukic209.workers.dev/mcp"
    }
  }
}
  1. Restart Cursor. The first time you use an Aurora tool, a browser window will open for authentication.

Authentication

Aurora's MCP server uses OAuth 2.1 — the same secure standard used by Google, GitHub, and other platforms. Here's how it works:

  1. You ask your AI assistant to use an Aurora tool (e.g. "List my campaigns")
  2. Your AI client automatically opens a browser window
  3. You sign in with your Aurora Intelligence account (the same email/password you use on aurora-intelligence.tech)
  4. After signing in, the browser redirects back and your AI client is connected

No API keys, no tokens to copy, no secrets to manage. The token is stored by your AI client and lasts for 7 days. After that, you'll be asked to sign in again.

Example Queries

Once connected, try asking your AI assistant:

  • "List my Aurora campaigns"
  • "Show brand visibility for my campaign over the last 30 days"
  • "Which domains are most cited by AI providers for my tracked queries?"
  • "Compare keyword frequency across ChatGPT and Gemini for campaign X"

Want to see full workflow examples with real responses? Check out the Use Cases page.