MCP.so
登录

MCP Client

@kamusis

代码仓库

关于 MCP Client

A lightweight TypeScript client for the Model Context Protocol (MCP) that enables AI language models to access external tools and services.

#typescript#mcp#model-context-protocol#mcp-server#mcp-client

基本信息

分类

其他

运行时

node

传输方式

stdio

发布者

kamusis

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "mcp-client-kamusis": {
      "command": "node",
      "args": [
        "build/index.js"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is MCP Client?

MCP Client is a TypeScript implementation of a client for the Model Context Protocol (MCP) that enables language models such as OpenAI’s GPT and Anthropic’s Claude to connect to and use external MCP server tools and services. It is designed for developers who need a standardized way to give LLMs access to external tools.

How to use MCP Client?

After cloning the repository and installing dependencies (npm install), create a .env file with your API keys and LLM provider selection (OPENAI or ANTHROPIC). Configure MCP servers in mcp_config.json by specifying the command, arguments, and optional environment variables. Build the project with npm run build and run it with node build/index.js.

Key features of MCP Client

  • Connects to multiple MCP servers simultaneously
  • Supports both OpenAI and Anthropic language models
  • Cross‑platform compatibility (Windows, macOS, Linux)
  • Automatic handling of platform‑specific commands (e.g., npx.cmd)
  • Configurable environment variables and server settings

Use cases of MCP Client

  • Giving an LLM access to a PostgreSQL database via an MCP server
  • Integrating a sequential‑thinking reasoning tool with a language model
  • Running multiple external tools (filesystem, web search, etc.) for a single LLM session

FAQ from MCP Client

What prerequisites are needed to run MCP Client?

Node.js (v16+), npm or yarn, and TypeScript are required.

How do I configure which LLM to use and which MCP servers to connect to?

Set the LLM environment variable to OPENAI or ANTHROPIC and provide the corresponding API key. Define your MCP servers in a mcp_config.json file, with each server specifying a command, arguments, and optional environment variables.

Which language model providers are supported?

OpenAI (e.g., gpt-4o) and Anthropic (e.g., claude-3-5-sonnet-20241022).

Does MCP Client handle platform‑specific differences?

Yes. On Windows, npx commands are automatically adjusted to npx.cmd, and Python commands use python on Windows vs. python3 on Unix‑like systems.

Where is the MCP configuration file located by default?

It defaults to ./mcp_config.json in the project root. You can override the path with the MCP_CONFIG_PATH environment variable.

评论

其他 分类下的更多 MCP 服务器

Awesome-MCP-ZH

yzfly

MCP 资源精选， MCP指南，Claude MCP，MCP Servers, MCP Clients

7.4K

Codelf

unbug

A search tool helps dev to solve the naming things problem.

14.2K

Reactive Resume

amruthpillai

A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!

39.5K

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K

ghidraMCP

LaurieWired

MCP Server for Ghidra

9.4K