remote-mcp-server-authless
A remote MCP server deployed on Cloudflare Workers that provides Cloudflare observability tools (zone analytics, workers analytics, web analytics) and basic calculator functions, without requiring authentication.
README
Building a Remote MCP Server on Cloudflare (Without Auth)
This example allows you to deploy a remote MCP server that doesn't require authentication on Cloudflare Workers. This server includes Cloudflare observability tools for monitoring your websites and Workers.
Get started:
This will deploy your MCP server to a URL like: remote-mcp-server-authless.<your-account>.workers.dev/sse
Alternatively, you can use the command line below to get the remote MCP Server created on your local machine:
npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless
Running Locally
You can run this MCP server locally for development and testing:
-
Install dependencies:
npm install -
Start the development server:
npm run dev # or npm startYour MCP server will be running at
http://localhost:8787/ -
Test with MCP Inspector:
npx @modelcontextprotocol/inspectorIn the inspector:
- Set Transport Type to
SSE - Enter
http://localhost:8787/sseas the server URL - Click "Connect"
- Set Transport Type to
-
Connect from Claude Desktop: Use the mcp-remote proxy in your Claude Desktop config:
{ "mcpServers": { "cloudflare-mcp": { "command": "npx", "args": [ "mcp-remote", "http://localhost:8787/sse" ] } } }
Available Tools
Calculator Tools
add- Simple additioncalculate- Calculator with multiple operations (add, subtract, multiply, divide)
Cloudflare Observability Tools
Zone Analytics
-
cloudflare_zone_analytics- Get analytics summary for a Cloudflare zone- Returns: total requests, bandwidth, unique visitors, threats blocked, page views
- Parameters:
zone_id,api_token,since(optional),until(optional)
-
cloudflare_zone_analytics_timeseries- Get time series analytics data- Returns: Detailed time series data with requests, bandwidth, visitors, threats over time
- Parameters:
zone_id,api_token,since(optional),until(optional)
Zone Management
cloudflare_list_zones- List all zones in your account- Returns: Zone IDs, names, status, plan, and creation dates
- Parameters:
api_token,name(optional filter)
Workers Analytics
cloudflare_workers_analytics- Query Workers Analytics Engine- Execute SQL-like queries against your Workers Analytics Engine datasets
- Parameters:
account_id,api_token,dataset(optional),query
Web Analytics
cloudflare_web_analytics- Get Web Analytics data for a site- Returns: Web Analytics statistics for your site
- Parameters:
account_id,site_tag,api_token,start(optional),end(optional)
Getting Cloudflare API Tokens
To use the Cloudflare observability tools, you'll need API tokens with appropriate permissions:
- Go to Cloudflare Dashboard
- Click "Create Token"
- Use "Edit zone DNS" template or create a custom token with:
- Zone Analytics:Read - For zone analytics tools
- Zone:Read - For listing zones
- Account Analytics:Read - For Workers and Web Analytics
- Copy the token (you'll only see it once!)
Finding Your Zone ID and Account ID
- Zone ID: Found in your Cloudflare dashboard under your domain's overview page
- Account ID: Found in the right sidebar of your Cloudflare dashboard
Example Usage
Get Zone Analytics
Tool: cloudflare_zone_analytics
Parameters:
- zone_id: "your-zone-id"
- api_token: "your-api-token"
- since: "2024-01-01T00:00:00Z" (optional)
- until: "2024-01-31T23:59:59Z" (optional)
List Your Zones
Tool: cloudflare_list_zones
Parameters:
- api_token: "your-api-token"
- name: "example.com" (optional)
Query Workers Analytics
Tool: cloudflare_workers_analytics
Parameters:
- account_id: "your-account-id"
- api_token: "your-api-token"
- query: "SELECT * FROM dataset LIMIT 10"
- dataset: "default" (optional)
Customizing your MCP Server
To add your own tools to the MCP server, define each tool inside the init() method of src/index.ts using this.server.tool(...).
Connect to Cloudflare AI Playground
You can connect to your MCP server from the Cloudflare AI Playground, which is a remote MCP client:
- Go to https://playground.ai.cloudflare.com/
- Enter your deployed MCP server URL (
remote-mcp-server-authless.<your-account>.workers.dev/sse) - You can now use your MCP tools directly from the playground!
Connect Claude Desktop to your MCP server
You can also connect to your remote MCP server from local MCP clients, by using the mcp-remote proxy.
To connect to your MCP server from Claude Desktop, follow Anthropic's Quickstart and within Claude Desktop go to Settings > Developer > Edit Config.
Update with this configuration:
{
"mcpServers": {
"cloudflare-mcp": {
"command": "npx",
"args": [
"mcp-remote",
"http://localhost:8787/sse" // or remote-mcp-server-authless.your-account.workers.dev/sse
]
}
}
}
Restart Claude and you should see the tools become available.
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。