
Create MCP
A CLI tool that sets up a Model Control Protocol server and deploys it to Cloudflare Workers, allowing you to quickly create custom tools for your Cursor Agent just by writing TypeScript functions.
README
create-mcp
A CLI tool that sets up a Model Control Protocol (MCP) server and deploys it to Cloudflare Workers so you can start making new tools for your Cursor Agent in minutes.
Just write TypeScript functions with JSDoc comments to give your agent MCP tools.
Prerequisites
- Wrangler CLI installed and logged in with your Cloudflare account.
- Claude Desktop App installed. (This will be removed soon)
Instructions
To scaffold and deploy a new MCP server, just run:
bun create mcp
You can also pass a name directly to the command: bun create mcp --name <server-name>
.
What this CLI does
- Clones the template worker repository into
<current-dir>/<server-name>
- Installs dependencies
- Initializes a Git repository
- Deploys a Hello World MCP server to your Cloudflare account
- Adds it to Claude Desktop
- Copies the MCP server command to your clipboard so you can paste it into Cursor
How to Use
Just add functions to the MyWorker
class in src/index.ts
. Each function will compile into an MCP tool.
For example:
/**
* A warm, friendly greeting from your new Workers MCP server.
* @param name {string} the name of the person we are greeting.
* @return {string} the contents of our greeting.
*/
sayHello(name: string) {
return `Hello from an MCP Worker, ${name}!`;
}
- The first line is the tool's description.
- The
@param
tags are the tool's params, with types and descriptions. - The
@return
tag is the tool's return value, with its type.
Deploying Changes
- Redeploy the worker:
bun run deploy
- Reload your Cursor window.
Now you can ask your agent to use the new tool!
Why Cloudflare Workers?
Vibes, great DX, and blazing fast deployments.
I don't like running MCP servers locally, and I'm pretty sure you don't either. Now we don't have to run node processes to use simple MCP tools in Cursor that call APIs.
All you have to do is write functions. Put your descriptions and params in JSDoc comments and it just works.
Example Servers made with create-mcp
You can clone and deploy any MCP server made with create-mcp to your own Cloudflare account:
bun create mcp --clone <github-url>
推荐服务器

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。
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。
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。
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。

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。
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。
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。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。