ee-mcp-server/README.md

Model Context Protocol server for Evolution Engineering

# Evolution Engineering MCP Server

A Model Context Protocol (MCP) server for Evolution Engineering, allowing AI models to query and interact with Evolution Engineering AI Tools.

## Overview

This project implements a server that follows the Model Context Protocol (MCP) specification to connect AI models with Evolution Engineering Toolset. The server translates and routes MCP requests to Evolution Engineering and formats the responses according to the MCP standard.

## Prerequisites

* Node.js (v16 or later)
* npm or yarn
* Evolution Engineering instance (running locally or remotely)

## Installation

1. Clone this repository:

   ```bash
   git clone https://github.com/EvolutionEngineering/ee-mcp-server
   cd ee-mcp-server
   ```
2. Install dependencies:

   ```bash
   npm install
   ```
3. Copy the example environment file and configure it:

   ```bash
   cp .env.example .env
   ```

   Edit `.env` with your configuration details.

## Configuration

Configuration is managed through environment variables in the `.env` file:
* `EE_API_KEY`: API key for authenticating MCP requests

## Usage

### Development

Start the development server with hot-reloading:

```bash
npm run dev
```

## MCP Test

To test distributed ee-mcp-server package you can run MCP inspector as:
npx -y @modelcontextprotocol/inspector npx ee-mcp-server

To test locally built ee-mcp-server package you can run MCP inspector as:
npx -y @modelcontextprotocol/inspector node ./dist/index.js


### Production

Build and start the server:

```bash
npm run build
npm start
```

## MCP Tools

* `get-model-metadata`: Get metadata about the EE instance and available capabilities
* `is-api-key-valid`: Validates EE API key and tests connection to EE Server
* `list-graphs`: List all available EE Graphs
* `query-graph`: Query EE Graph
* `get-model-semantic-ontology`: Query Semantic Ontology provided by EE

## MCP Configuration

To use this server with MCP clients, you can add it to your MCP configuration:

```json
{
  "defaultServer": "ee-mcp-server",
  "servers": {
    "ee-mcp-server":{
      "command": "node",
        "args": [
        "your_path\\dist\\index.js"
        ],
      "env": {
          "EE_API_KEY": "your_EE_MCP_API_KEY"
        }
    }
  }
}

Alternatively, instead of environment variable specification EE_API_KEY, you can provide "apiKey" parameter value directly from MCP client

## License

This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.