MCP Conversation Server

🚀 MCP Conversation Server

An implementation of the Model Context Protocol (MCP) server for managing conversations with language models on OpenRouter. This server provides a standardized interface for applications to interact with multiple language models through a unified conversation management system.

🚀 Quick Start

Installation

npm install mcp-conversation-server

Configuration

All configurations for the MCP conversation server are now provided via YAML. Please update the config/models.yaml file to set your options. For example:

# MCP server configuration
openRouter:
  apiKey: "YOUR_OPENROUTER_API_KEY"  # Replace with your actual OpenRouter API key.

persistence:
  path: "./conversations"  # Directory to store conversation data.

models:
  # Define your models here
  'provider/model-name':
    id: 'provider/model-name'
    contextWindow: 123456
    streaming: true
    temperature: 0.7
    description: 'Model description'

# Use this model by default if not specified
defaultModel: 'provider/model-name'

Server Configuration

The MCP conversation server now loads all configurations from a YAML file. In your application, you can load the configuration as follows:

const config = await loadModelsConfiguration();

Usage Instructions

• Install Dependencies

  • Ensure Node.js and npm are installed.
  • Run npm install to install all dependencies.

• Run the Server

node index.js

✨ Features

• MCP Protocol Support

  • Fully compliant with the MCP protocol
  • Resource management and discovery
  • Tool-driven interaction mode
  • Support for streaming responses
  • Error handling and recovery

• OpenRouter Integration

  • Supports all OpenRouter models
  • Real-time streaming responses
  • Automatic token counting
  • Context window management
  • Available models include:
    • Claude 3 Opus
    • Claude 3 Sonnet
    • Llama 2 70B
    • Many other models in the OpenRouter catalog

• Conversation Management

  • Create and manage multiple conversations
  • Supports system messages
  • Message history tracking
  • Token usage monitoring
  • Conversation filtering and search

• Streaming Support

  • Real-time message streaming
  • Chunked response handling
  • Token counting

• File System Persistence

  • Persistence of conversation states
  • Storage location configuration
  • Automatic state management

📚 Documentation

Development

1. Refer to the documentation to learn how to contribute.
2. Fork the repository.
3. Create a feature branch.
4. Commit your changes.
5. Push to the branch.
6. Create a Pull Request.

📄 License

ISC License