Context Server

TypeScript toolkit for creating, interacting with, and monitoring clients and servers using the Model Context Protocol (MCP).

Features

• MCP Server & Client - Full protocol implementation
• Multi-Context Host - Manage multiple MCP servers with tool namespacing
• Session Management - High-level chat abstraction with tool calling
• Agent Loop - Automatic tool execution with configurable approval
• Model Providers - OpenAI, Anthropic, and Ollama integration
• Monitoring - Real-time observation of MCP traffic
• CLI - Interactive chat and server inspection tools

Quick Start

npm install @mokei/session @mokei/openai-provider

import { Session } from '@mokei/session'
import { OpenAIProvider } from '@mokei/openai-provider'

const session = new Session({
  providers: {
    openai: OpenAIProvider.fromConfig({
      apiKey: process.env.OPENAI_API_KEY
    })
  }
})

// Add an MCP server
await session.addContext({
  key: 'myserver',
  command: 'node',
  args: ['my-mcp-server.js']
})

// Chat with tool access
const response = await session.chat({
  provider: 'openai',
  model: 'gpt-4',
  messages: [{ source: 'client', role: 'user', text: 'Hello!' }]
})

Documentation

• Full Documentation - Complete guides and API reference
• Quick Start Guide - Get running in minutes
• docs/ - Local documentation

Packages

CLI

mokei monitor            # Start the monitor UI for MCP server traffic
mokei inspect            # Inspect an MCP server (prints its initialize result)
mokei chat -p openai     # Interactive chat

Contributing

See AGENTS.md for development setup and code style guidelines.

License

MIT