GitHub MCP server

This is a Model Context Protocol (MCP) server implementation that allows communication between various client applications and AI models. It provides a standardized way to manage AI model interactions, handling context management and token optimization.

Installation

Prerequisites

• Node.js (version 18 or higher)
• npm (comes with Node.js)

Install from npm

The simplest way to install the MCP server is via npm:

npm install -g ia-mcp-server

Manual Installation

Alternatively, you can clone the repository and install dependencies:

git clone https://github.com/user/ia-mcp-server.git
cd ia-mcp-server
npm install

Starting the Server

Basic Usage

Start the server with default settings:

mcp-server

This will start the server on the default port (3000).

Configuration Options

You can configure the server by passing command line arguments:

mcp-server --port 8080 --host 0.0.0.0

Available options:

• --port: Specify the port number (default: 3000)
• --host: Specify the host address (default: localhost)
• --config: Path to a configuration file
• --ssl-cert: Path to SSL certificate
• --ssl-key: Path to SSL key

Using a Configuration File

Create a JSON configuration file:

{
  "port": 8080,
  "host": "0.0.0.0",
  "models": [
    {
      "name": "gpt4",
      "endpoint": "https://api.example.com/v1/completions",
      "apiKey": "your-api-key-here"
    }
  ]
}

Start the server with your configuration:

mcp-server --config ./my-config.json

Using the MCP Server

Connecting to the Server

Applications can connect to the MCP server using WebSockets. The connection URL format is:

ws://localhost:3000/mcp

If you've configured SSL:

wss://localhost:3000/mcp

API Endpoints

The server provides several REST API endpoints:

• GET /models - Lists available models
• GET /status - Server status information
• POST /completion - Generate a completion (synchronous)

Example: Getting Available Models

curl http://localhost:3000/models

Response:

{
  "models": [
    {
      "id": "gpt4",
      "capabilities": ["completion", "chat", "embedding"]
    }
  ]
}

Example: Sending a Completion Request

curl -X POST http://localhost:3000/completion \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt4",
    "prompt": "Hello, how are you?",
    "max_tokens": 100
  }'

Troubleshooting

Common Issues

• Connection refused: Ensure the server is running and the port is correct
• Authentication failed: Check your API keys in the configuration
• Model not found: Verify the model name exists in your configuration

Logs

The server logs are helpful for diagnosing issues:

mcp-server --log-level debug

Log levels: error, warn, info, debug

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "ia-mcp" '{"command":"npx","args":["-y","ia-mcp"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "ia-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "ia-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "ia-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "ia-mcp"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect