一种基于 LLM 代理的模型上下文协议（MCP）客户端的 TypeScript 实现。

安装

特色

• MCP规范的完整实现
• 支持 stdio 和 HTTP+SSE 传输
• 内置MCP服务器进程管理
• 与 Claude 原生工具调用集成
• 类型安全 API
• 基于事件的架构
• 基于承诺的异步/等待API
• 支持所有MCP操作：
• 资源
• 工具
• 提示
• 抽样

用途

使用 MCP 服务器

使用 MCP 客户端最常见的方式是通过 npx 与标准 MCP 服务器连接。创建一个配置文件（mcp-config.json）：

然后用MCPConnectionManager连接到你的服务器：

与克劳德的融合

该客户端设计为无缝兼容 Claude 原生工具调用：

低层次使用

如果你需要更多控制，可以直接使用客户端：

可用MCP服务器

通过npx提供的常见MPC服务器：

• @modelcontextprotocol/server-memory - 知识图谱操作
• @modelcontextprotocol/server-filesystem - 文件系统操作
• @modelcontextprotocol/server-brave-search - 网页搜索功能

MCP Client

A TypeScript implementation of a Model Context Protocol (MCP) client for LLM agents.

Installation

npm install mcp-client

Features

• Full implementation of the MCP specification
• Support for both stdio and HTTP+SSE transports
• Built-in MCP server process management
• Integration with Claude’s native tool calling
• Type-safe API
• Event-based architecture
• Promise-based async/await API
• Support for all MCP operations:
  • Resources
  • Tools
  • Prompts
  • Sampling

Usage

Using with MCP Servers

The most common way to use MCP Client is with standard MCP servers via npx. Create a configuration file (mcp-config.json):

{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-memory"
      ]
    },
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "/path/to/allowed/directory"
      ]
    },
    "brave-search": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-brave-search"
      ],
      "env": {
        "BRAVE_API_KEY": "your-api-key"
      }
    }
  }
}

Then use the MCPConnectionManager to connect to your servers:

import { MCPConnectionManager } from 'mcp-client';

const manager = new MCPConnectionManager();
await manager.initialize('./mcp-config.json');

// Get clients for specific servers
const memoryClient = manager.getClient('memory');
const fsClient = manager.getClient('filesystem');

// Use tools from the servers
const memoryTools = await memoryClient?.listTools();
const fsTools = await fsClient?.listTools();

// Clean up when done
await manager.cleanup();

Integration with Claude

The client is designed to work seamlessly with Claude’s native tool calling:

import { Anthropic } from '@anthropic-ai/sdk';
import { MCPConnectionManager } from 'mcp-client';

// Initialize Claude and MCP
const anthropic = new Anthropic({ apiKey: process.env.ANTHROPIC_API_KEY });
const manager = new MCPConnectionManager();
await manager.initialize('./mcp-config.json');

// Get a client
const memoryClient = manager.getClient('memory');
const tools = await memoryClient?.listTools();

// Use with Claude
const response = await anthropic.messages.create({
  model: 'claude-3-sonnet-20240229',
  max_tokens: 1024,
  messages: [{ role: 'user', content: 'your prompt' }],
  tools: tools?.map(tool => ({
    name: tool.name,
    description: tool.description || '',
    parameters: tool.inputSchema
  }))
});

// Handle tool calls
if (!response.content[0].text && response.content[0].type === 'tool_call') {
  const toolCall = response.content[0].tool_calls[0];
  const result = await memoryClient?.callTool(
    toolCall.name,
    toolCall.parameters
  );
  // Send result back to Claude...
}

Low-level Usage

If you need more control, you can use the client directly: