Brightsy MCP

🚀 Brightsy MCP Server

This is a Model Context Protocol (MCP) server that connects to the Brightsy AI agent, facilitating seamless interaction with the AI.

🚀 Quick Start

✨ Features

• Connects to the Brightsy AI agent.
• Allows customization of tool names.
• Supports configuration through environment variables and command - line arguments.
• Provides testing scripts for the agent_proxy tool.

📦 Installation

npm install

💻 Usage Examples

Basic Usage

Start the server:

npm start -- --agent-id=<your-agent-id> --api-key=<your-api-key>

Or use positional arguments:

npm start -- <your-agent-id> <your-api-key> [tool-name] [message]

You can also provide an initial message to send to the agent:

npm start -- --agent-id=<your-agent-id> --api-key=<your-api-key> --message="Hello, agent!"

Advanced Usage

Customizing Tool Name

By default, the MCP server registers a tool named "brightsy". You can customize the name using the --tool-name parameter:

npm start -- --agent-id=<your-agent-id> --api-key=<your-api-key> --tool-name=<custom-tool-name>

You can also set the tool name as the third positional argument:

npm start -- <your-agent-id> <your-api-key> <custom-tool-name>

Or use the environment variable BRIGHTSY_TOOL_NAME:

export BRIGHTSY_TOOL_NAME=custom-tool-name
npm start -- --agent-id=<your-agent-id> --api-key=<your-api-key>

Environment Variables

The following environment variables can be used to configure the server:

• BRIGHTSY_AGENT_ID: The ID of the agent to use (alternative to command - line arguments).
• BRIGHTSY_API_KEY: The API key to use (alternative to command - line arguments).
• BRIGHTSY_TOOL_NAME: The name of the registered tool (default: "brightsy").

📚 Documentation

Testing the agent_proxy Tool

The agent_proxy tool allows you to proxy requests to the Brightsy AI agent. You can use the provided test scripts to test it.

Prerequisites

Before running the tests, set the following environment variables:

export AGENT_ID=your-agent-id
export API_KEY=your-api-key
# Optional: Customize the tool name for testing
export TOOL_NAME=custom-tool-name

Or pass these values via command - line arguments:

# Use named arguments
npm run test:cli -- --agent-id=your-agent-id --api-key=your-api-key --tool-name=custom-tool-name

# Use positional arguments
npm run test:cli -- your-agent-id your-api-key custom-tool-name

Running Tests

Run all tests:

npm test

Run specific tests:

# Test the command - line interface
npm run test:cli

# Test the direct MCP protocol
npm run test:direct

Test Scripts

1. Command - line Test (test-agent-proxy.ts): Tests the agent_proxy tool by running the MCP server and sending test messages.
2. Direct MCP Protocol Test (test-direct.ts): Tests the agent_proxy tool by sending a well - formatted MCP request directly to the server.

How the Tool Works

The MCP server registers a tool (default name: "brightsy") that forwards requests to an OpenAI - compatible AI agent and returns the response. It accepts a messages parameter, which is an array of message objects, each with role and content properties.

Example usage (in an MCP client):

// Use the default tool name
const response = await client.callTool("brightsy", {
  messages: [
    {
      role: "user",
      content: "Hello, can you help me with a simple task?"
    }
  ]
});

// Or use a custom tool name (if configured)
const response = await client.callTool("custom-tool-name", {
  messages: [
    {
      role: "user",
      content: "Hello, can you help me with a simple task?"
    }
  ]
});

The response will contain the agent's reply in the content field.