Skip to main content
Glama
MatthewDailey

MCP Starter Server

MCP 入门服务器

用于构建 AI 助手工具的极简ModelContextProtocol服务器模板。此入门模板提供了创建可与 Claude 等 AI 助手配合使用的 MCP 工具的基本结构。

特征

  • 简单的“hello world”工具示例

  • TypeScript + esbuild 设置

  • 预配置的开发工具

Related MCP server: MCP Server Scaffold

设置以使用 Claude 进行构建和运行

  1. claude.ai/download下载并安装 Claude 桌面应用程序

  2. 克隆 repo、安装依赖项并构建:

npm install
npm run build
  1. 配置 Claude 使用此 MCP 服务器。如果这是您的第一个 MCP 服务器,请在项目的根目录中运行:

echo '{
  "mcpServers": {
    "mcp-starter": {
      "command": "node",
      "args": ["'$PWD'/dist/index.cjs"]
    }
  }
}' > ~/Library/Application\ Support/Claude/claude_desktop_config.json

这应该会导致您的claude_desktop_config.json中出现如下条目:

"mcpServers": {
  "mcp-starter": {
    "command": "node",
    "args": ["/Users/matt/code/mcp-starter/dist/index.cjs"]
  }
}

如果您已有 MCP 服务器,请将mcp-starter块添加到现有配置中。需要注意的是, args<path_to_repo_on_your_machine>/mcp-starter/dist/index.cjs的路径。

  1. 重新启动 Claude Desktop。

  2. 在 Claude 的界面中查找带有可用工具数量的锤子图标,以确认服务器正在运行。

  3. 如果一切顺利,您应该能够使用npm run dev开发您的 MCP 服务器,并在 Claude 中测试它。每次重启 Claude 时,您都需要重启 MCP 服务器。

使用 Inspector 进行开发

您可以使用 MCP Inspector 工具进行开发和调试。该工具提供了一个可视化界面,用于测试和监控 MCP 服务器的交互。

请访问Inspector 文档以获取详细的设置说明。

使用 Inspector 进行本地测试:

npm run inspect

要基于文件更改进行构建,请运行:

npm run watch

或者同时运行观察者和检查者:

npm run dev

出版

一旦您准备好分发服务器,一切都很简单!

  1. 设置NPM帐户。

  2. 运行npm publish 。这将使用package.json中的项目名称发布一个包

  3. 一旦发布,其他人就可以使用如下配置条目安装服务器:

"mcpServers": {
  "<your-package-name>": {
    "command": "npx",
    "args": ["<your-package-name>"]
  }
}

可用工具

服务器提供:

  • hello_tool :一个简单的示例工具,它接受一个名称参数并返回问候语

创建新工具

要添加新工具:

  1. index.ts中定义工具架构

  2. 将其添加到ListToolsRequestSchema处理程序中的工具数组中

  3. CallToolRequestSchema处理程序中添加实现

请参阅hello_tool实现作为示例。

Install Server
A
license - permissive license
C
quality
D
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • F
    license
    B
    quality
    D
    maintenance
    A basic starter project for building Model Context Protocol (MCP) servers that enables standardized interactions between AI systems and various data sources through secure, controlled tool implementations.
    2
  • F
    license
    Not graded
    quality
    D
    maintenance
    A minimal Model Context Protocol server built with FastAPI that provides a basic "Hello World" resource and tool. Serves as a starting point for building and validating MCP client integrations with richer resources and tools.
  • A
    license
    Not graded
    quality
    D
    maintenance
    A bare-bones FastMCP server template designed to serve as a starting point for building custom Model Context Protocol servers. It provides a foundational structure for implementing tools over HTTP and includes a built-in health check utility.
    GPL 3.0

View all related MCP servers

Related MCP Connectors

  • A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…

  • A Model Context Protocol server for Wix AI tools

  • MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/MatthewDailey/mcp-starter'

If you have feedback or need assistance with the MCP directory API, please join our Discord server