Fledge IoT

🚀 Fledge MCP Server

This is a Model Context Protocol (MCP) server that connects Fledge functionality to Cursor AI, allowing the AI to interact with Fledge instances via natural language commands.

🚀 Quick Start

The Fledge MCP Server serves as a bridge between Fledge and Cursor AI, enabling seamless interaction through natural - language commands.

✨ Features

• Supports the JSON - RPC 2.0 protocol over WebSocket.
• Provides the following tools:
  • Retrieve sensor data.
  • Control devices.
  • Get system status.
  • Obtain log information.
  • Set alarm thresholds.

📦 Installation

Prerequisites

• Fledge installed locally or accessible via API (default: http://localhost:8081).
• Cursor AI installed.
• Python 3.8+.

Steps

1. Clone this repository:

git clone https://github.com/Krupalp525/fledge-mcp.git
cd fledge-mcp

2. Install dependencies:

pip install -r requirements.txt

💻 Usage Examples

Basic Usage

1. Start the server:

python mcp_server.py

2. Access http://localhost:8082 in your browser to view the documentation.

Advanced Usage

Example Requests

1. Initialization:

{
    "jsonrpc": "2.0",
    "method": "initialize",
    "params": {},
    "id": "1"
}

2. List tools:

{
    "jsonrpc": "2.0",
    "method": "tools/list",
    "params": {},
    "id": "2"
}

3. Call a tool:

{
    "jsonrpc": "2.0",
    "method": "tools/call",
    "params": {
        "name": "get_sensor_data",
        "parameters": {
            "sensor_id": "temp1",
            "limit": 10
        }
    },
    "id": "3"
}

Error Codes

The server follows the standard JSON - RPC 2.0 error codes:

• -32700: Parse error.
• -32600: Invalid request.
• -32601: Method not found.
• -32602: Invalid parameters.
• -32000: Server error.

📚 Documentation

Considerations for Production Environment

• Use HTTPS.
• Deploy behind a reverse proxy (e.g., Nginx).
• Implement stronger authentication (JWT, OAuth).
• Add rate limiting.
• Set up persistent data storage for subscriptions.

Deployment on Smithery.ai

1. Prerequisites

   • Docker installed.
   • A Smithery.ai account.
   • Smithery CLI tool installed.

2. Build and Deploy

# Build the Docker image
docker build -t fledge-mcp .

# Deploy to Smithery.ai
smithery deploy

3. Configuration

   • WebSocket transport on port 8082.
   • Configurable Fledge API URL.
   • Tool definitions and parameters.
   • Timeout settings.

4. Environment Variables

   • FLEDGE_API_URL: Your Fledge API endpoint.
   • API_KEY: Your security - mode API key.

5. Verification

smithery status fledge-mcp

6. Monitoring

• Monitor real - time logs, performance metrics, error tracking, and resource usage through the Smithery.ai console.

7. Update

# Build a new image
docker build -t fledge-mcp .
   
# Deploy the update
smithery deploy --update

JSON - RPC Protocol Support

The server implements the Model Context Protocol (MCP) using the JSON - RPC 2.0 protocol.

Supported Methods

1. initialize

   {
       "jsonrpc": "2.0",
       "method": "initialize",
       "params": {},
       "id": "1"
   }
   

   Response:

   {
       "jsonrpc": "2.0",
       "result": {
           "serverInfo": {
               "name": "fledge-mcp",
               "version": "1.0.0"
           }
       },
       "id": "1"
   }