IoT Realm MCP Server 🌐🔌

An MCP server that exposes real-time sensor data from IoT Realm devices—such as ESP32-based DHT11 clients—to LLMs via the Model Context Protocol. This enables AI agents to access, analyze, and act upon live environmental data.

🧠 What It Does

• Connects to the IoT Realm Server: Fetches data from devices like AtmosWatcher.
• Exposes MCP Tools: Provides tools for LLMs to retrieve sensor readings.
• Provides Resources: Offers structured data resources for AI consumption.
• Supports Prompts: Includes predefined prompts to guide LLM interactions.

🚀 Features

• 🔄 Real-Time Data Access: LLMs can query current sensor values.
• 🛠️ MCP-Compliant Tools: Implements tools following MCP standards.
• 📚 Structured Resources: Supplies data in formats suitable for AI models.
• 🧾 Predefined Prompts: Facilitates natural language interactions.

🧰 Tools

• get_realm_structure: Get the structure of the IoT realm.
• get_value: Get a specific value from the IoT realm.
• set_value: Set a specific value in the IoT realm.

🛠️ Installation

1. Clone the Repository:

   git clone https://github.com/PerikiyoXD/iot-realm-mcp-server.git
   cd iot-realm-mcp-server
   

2. Install Dependencies:

   uv venv
   uv pip install -e .
   

3. Configure Environment Variables: Create a .env file with the following content:

   IOT_REALM_SERVER_URL=http://localhost:6699
   

🏃 Running the Server

Start the MCP server using:

uv venv
uv run iot-realm-mcp-server

The server will be accessible to MCP clients like Claude Desktop.

🔗 Integration with Claude Desktop

To integrate with Claude Desktop:

1. Open Claude Desktop settings.
2. Add a new MCP server with the path to iot_realm_mcp_server.
3. Use the provided tools and prompts to interact with your IoT devices.

📄 License

MIT License – use it, fork it, hack it.

👤 Author

PerikiyoXD
💻 github.com/PerikiyoXD
📡 Connecting solutions to problems, because people should look for real solutions.

Made with FastAPI, uvicorn, and a passion for open-source IoT solutins.