Setup Guide

Before you start, you need:

1. An API Key — You'll receive an API key once your waitlist application is approved. It looks like tk_live_abc123...
2. An AI Tool — Claude Code, Cursor, Windsurf, or any MCP-compatible client.

The easiest way to get started. First, configure npm to use the private registry (one-time setup):

echo "@titan-agentic-ai:registry=https://npm.pkg.github.com" >> .npmrc

Install the TitanConnect plugin:

npm install @titan-agentic-ai/connect-openclaw

Set your API key as an environment variable:

export TITAN_API_KEY="YOUR_API_KEY"

Add the plugin to your OpenClaw configuration:

{
  "plugins": ["@titan-agentic-ai/connect-openclaw"]
}

The plugin registers all 28 tools automatically and includes a comprehensive teaching document so your AI knows how to use every tool effectively.

Run this single command in your terminal:

claude mcp add \
  --transport streamable-http \
  titan-connect \
  https://staging-titanconnect.vynta.ai/api/mcp \
  --header "Authorization: Bearer YOUR_API_KEY"

Replace YOUR_API_KEY with your actual API key.

That's it. Start a new Claude Code session and you'll have access to all 28 tools. Try asking: "Show me my PPC performance for the last 30 days"

Add TitanConnect to your Cursor MCP configuration file:

{
  "mcpServers": {
    "titan-connect": {
      "url": "https://staging-titanconnect.vynta.ai/api/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Create this file in your project root (or home directory for global access). Restart Cursor after saving. You'll see TitanConnect tools in the AI panel.

Windsurf uses the same MCP configuration format as Cursor:

{
  "mcpServers": {
    "titan-connect": {
      "url": "https://staging-titanconnect.vynta.ai/api/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Place this file in your project root. Restart Windsurf to activate.

Once connected, try these example prompts with your AI: