cursor-ia-consumption-tracker

A simplified MCP (Model Context Protocol) server for tracking AI consumption data from Cursor IDE with platform integration and token logging.

Features

• 🚀 Simple Setup - Easy integration with Cursor IDE via MCP
• 📊 Consumption Tracking - Automatic token usage and query analysis
• 🔄 Platform Integration - Sends data to your tracking platform
• 🎯 Agent Detection - Supports multiple AI agents (Claude, GPT, etc.)
• 📝 Clean Logging - Structured JSON logs with essential metrics
• ⚡ Lightweight - Minimal dependencies and overhead

Installation

Global Installation (Recommended)

npm install -g cursor-ia-consumption-tracker

Local Installation

npm install cursor-ia-consumption-tracker

Setup with Cursor IDE

1. Add to your Cursor MCP configuration (~/.cursor/mcp.json):

{
  "mcpServers": {
    "ia-consumption-tracker": {
      "command": "node",
      "args": ["node_modules/cursor-ia-consumption-tracker/auto-logger.js"],
      "env": {
        "PLATFORM_HOST": "https://your-platform.com",
        "PLATFORM_ROUTE": "/api/track",
        "CLIENT_ID": "your-client-id",
        "PROJECT_NAME": "your-project-name",
        "AGENT_NAME": "claude-4-sonnet"
      }
    }
  }
}

2. For global installation:

{
  "mcpServers": {
    "ia-consumption-tracker": {
      "command": "ia-consumption-mcp",
      "env": {
        "PLATFORM_HOST": "https://your-platform.com",
        "PLATFORM_ROUTE": "/api/track",
        "CLIENT_ID": "your-client-id",
        "PROJECT_NAME": "your-project-name",
        "AGENT_NAME": "claude-4-sonnet"
      }
    }
  }
}

Configuration

Environment Variables

| Variable | Description | Required | Default | |----------|-------------|----------|---------| | PLATFORM_HOST | Your tracking platform URL | Yes | https://localhost:8069 | | PLATFORM_ROUTE | API endpoint for tracking | Yes | /ia_tracker/track | | CLIENT_ID | Your client identifier | Yes | cursor_default_client | | PROJECT_NAME | Project name for tracking | Yes | cursor_mcp_logger | | AGENT_NAME | AI agent name | No | cursor-agent |

Usage

Once configured, the MCP server provides one tool:

send_consumption

Automatically tracks and sends consumption data for each chat interaction.

Parameters:

• user_query (required): The user's question/request
• response_length (optional): Actual response character count

Example Response:

📊 CONSUMPTION SENT: auto_1758109135068
Agent: claude-4-sonnet
Query: "Hello world"
Tokens: 5 (3+2)
Platform: Sent to https://your-platform.com/api/track

Data Structure

The consumption data sent to your platform includes:

{
  "cursor_data": {
    "request_id": "auto_1758109135068",
    "timestamp": "2024-01-20T10:30:00.000Z",
    "session_id": "session_12345_1705748200",
    "agent_name": "claude-4-sonnet",
    "agent_info": {
      "agent_name": "claude-4-sonnet",
      "session_agent": "claude-4-sonnet"
    },
    "request_data": {
      "type": "chat_completion",
      "query_text": "Hello world",
      "query_length": 11,
      "word_count": 2,
      "query_type": "general",
      "complexity": "low",
      "language": "english",
      "has_code": false
    },
    "token_metrics": {
      "input_tokens": 3,
      "output_tokens": 2,
      "total_tokens": 5,
      "estimation_method": "input_ratio_2.5x"
    },
    "session_context": {
      "total_interactions": 1,
      "workspace": "/path/to/workspace",
      "platform": "darwin"
    }
  }
}

Development

Local Development

# Clone the repository
git clone https://github.com/vunkers/ia-consumption-tracker.git
cd ia-consumption-tracker

# Install dependencies
npm install

# Start development server
npm run dev

Testing

npm test

Contributing

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Support

• 🐛 Issues: GitHub Issues
• 📖 Documentation: GitHub Wiki

Changelog

v1.0.0

• Initial release
• Simple consumption tracking
• Platform integration
• Agent detection support
• Cursor IDE integration

Made with ❤️ by Arkiphere Cloud LLC