TypeSpec MCP Server

TypeSpec MCP Server

Enables building MCP servers using TypeSpec, with tools to scaffold, compile, and learn TypeSpec.

Category
访问服务器

README

TypeSpec MCP Server and Emitter

Install with NPX in VS Code Install with NPX in VS Code Insiders

The TypeSpec MCP Server implements the MCP specification to enable you to quickly build out your own MCP servers powered by TypeSpec. We will also enable you to build REST APIs and other protocols supported by TypeSpec, though this is work in progress.

Please note that this project is in Public Preview and implementation may significantly change prior to our General Availability.

Overview

What packages are in this repository?

Currently this repo contains the following packages:

  • mcp-server-typespec - an MCP server which assists in developing MCP extensions using TypeSpec.
  • typespec-mcp - a TypeSpec library for describing MCP servers, for example the @tool decorator.
  • typespec-mcp-server-js - A TypeSpec emitter that generates a server implementation in JavaScript for an MCP tool.
  • typespec-mcp-http-server-js - A TypeSpec emitter that generates a server implementation in JavaScript for calling a remote REST API.

Currently Supported Tools

The TypeSpec MCP Server provides the following tools:

  • learnTypeSpec - Initializes the model with information about how to understand and write TypeSpec.
  • init - Scaffolds out a new project in the current working directory with example tool implementation.
  • compile - Runs tsp compile to generate emitter assets
  • build - Executes npm run build in the current project.

Getting Started

The TypeSpec MCP Server requires Node.js to install and run the server. If you don't have it installed, follow the instructions here.

VS Code + GitHub Copilot

The TypeSpec MCP Server provides assistance with authoring TypeSpec to generate MCP resource implementations. It can be used alone or with the TypeSpec VS Code extension in VS Code.

Prerequisites

  1. Install either the stable or Insiders release of VS Code:
  2. Install the GitHub Copilot and GitHub Copilot Chat extensions
  3. Install Node.js 20 or later
    • Ensure node and npm are in your path
  4. Open VS Code in an empty folder

Installation

One-Click Install

Click one of these buttons to install the TypeSpec MCP Server for VS Code or VS Code Insiders.

Install with NPX in VS Code Install with NPX in VS Code Insiders

Once you've installed the TypeSpec MCP Server, make sure you select GitHub Copilot Agent Mode and refresh the tools list. To learn more about Agent Mode, visit the VS Code Documentation.

Manual Install

For a step-by-step installation, follow these instructions:

  1. Add .vscode/mcp.json:
{
  "servers": {
    "TypeSpec MCP Server": {
      "command": "npx",
      "args": ["-y", "mcp-server-typespec@latest"]
    }
  }
}

Test the TypeSpec MCP Server

  1. Open GitHub Copilot in VS Code and switch to Agent mode
  2. You should see the TypeCpec MCP Server in the list of tools
  3. Try a prompt that tells the agent to use a TypeSpec MCP Server, such as "init" to scaffold a new project.

Troubleshooting

See Troubleshooting guide for help with common issues and logging.

Contributing

We welcome contributions to the TypeSpec MCP Server! Whether you're fixing bugs, adding new features, or improving documentation, your contributions are welcome.

Please read our Contributing Guide for more information on how to contribute.

Code of Conduct

This project has adopted the Microsoft Open Source Code of Conduct. For more information, see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选