MCP Server

A FastAPI server for integrating with the EAIM Technologies API and providing data visualization capabilities through WebSockets.

Features

- Natural language query processing to extract API parameters
- Integration with EAIM Technologies API
- WebSocket support for real-time updates
- Data visualization capabilities

API Endpoints

- /api/query - Process natural language queries
- /api/dashboards - Get available dashboards
- /api/visualizations/{dashboard_id} - Get available visualizations for a dashboard
- WebSocket at /api/ws for real-time communication

Setup

Prerequisites

- Python 3.9+
- pip

Installation

1. Clone the repository:

   git clone https://github.com/yourusername/mcp-server.git
   cd mcp-server
   

2. Install dependencies:

   pip install -r requirements.txt
   

3. Run the server:

   uvicorn app.main:app --reload

   

Docker

You can also run the server using Docker:

docker build -t mcp-server .
docker run -p 8000:8000 mcp-server

Usage

Send natural language queries like:

> "Show me the engagement of Vodafone Egypt over the last month"

The server will parse the query, extract relevant parameters, and make a request to the EAIM Technologies API.

WebSocket Example

const socket = new WebSocket("ws://localhost:8000/api/ws");
socket.onopen = () => {

  socket.send(

    JSON.stringify({

      type: "query",

      query: "Show me the engagement of Vodafone Egypt over the last month",

    })

  );

};
socket.onmessage = (event) => {

  const data = JSON.parse(event.data);

  console.log(data);

};