MCP.so
登录

Remote MCP Server on Cloudflare

@seedprod

代码仓库

关于 Remote MCP Server on Cloudflare

暂无概览

#remote-mcp-server#cloudflare#mcp-inspector

基本信息

分类

云与基础设施

运行时

node

传输方式

stdio

发布者

seedprod

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "remote-mcp-server-seedprod": {
      "command": "npx",
      "args": [
        "nx",
        "dev",
        "remote-mcp-server"
      ]
    }
  }
}

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 Remote MCP Server on Cloudflare?

Remote MCP Server on Cloudflare helps you run a Model Context Protocol (MCP) server on Cloudflare Workers, complete with OAuth login. It enables MCP clients to connect to the server remotely via Server-Sent Events (SSE).

How to use Remote MCP Server on Cloudflare?

Clone the repository, install dependencies with npm install, and run locally with npx nx dev remote-mcp-server. Deploy to Cloudflare by creating a KV namespace (npx wrangler kv namespace create OAUTH_KV), adding the namespace ID to wrangler.jsonc, then running npm run deploy. Connect MCP clients (like the MCP Inspector or Claude Desktop) using the SSE endpoint (e.g., http://localhost:8787/sse locally or https://worker-name.account-name.workers.dev/sse after deployment).

Key features of Remote MCP Server on Cloudflare

  • Runs MCP server on Cloudflare Workers.
  • Includes OAuth login flow.
  • Uses SSE transport for client connections.
  • Works with MCP Inspector for testing.
  • Integrates with Claude Desktop via the mcp-remote proxy.
  • Deployable to a workers.dev subdomain.

Use cases of Remote MCP Server on Cloudflare

  • Host a remote MCP server accessible from any MCP client.
  • Connect Claude Desktop to a remote MCP server over HTTP.
  • Test MCP tools locally with the MCP Inspector before deploying.
  • Run MCP tooling in a serverless environment with authentication.

FAQ from Remote MCP Server on Cloudflare

What is Remote MCP Server on Cloudflare?

It is a template to get a remote MCP server up‑and‑running on Cloudflare Workers, complete with OAuth login.

How do I connect Claude Desktop to my MCP server?

Add a configuration entry to Claude Desktop’s settings file using the mcp-remote proxy. For a local server, use "command": "npx", "args": ["mcp-remote", "http://localhost:8787/sse"]. For a deployed server, replace the URL with https://worker-name.account-name.workers.dev/sse.

How do I deploy the server to Cloudflare?

First create a KV namespace with npx wrangler kv namespace create OAUTH_KV, add its ID to wrangler.jsonc, then run npm run deploy.

How do I debug issues with the server?

Restart Claude, or test the connection directly with npx mcp-remote http://localhost:8787/sse. In rare cases, clear auth files with rm -rf ~/.mcp-auth.

How do I use the MCP Inspector with this server?

Start the inspector with npx @modelcontextprotocol/inspector, set Transport Type to SSE, and enter the server’s SSE URL (e.g., http://localhost:8787/sse). You will be prompted to login (mock credentials work locally), then you can list and call defined tools.

评论

云与基础设施 分类下的更多 MCP 服务器

K8s MCP Server

alexei-led

K8s-mcp-server is a Model Context Protocol (MCP) server that enables AI assistants like Claude to securely execute Kubernetes commands. It provides a bridge between language models and essential Kubernetes CLI tools including kubectl, helm, istioctl, and argocd, allowing AI syste

212

Sample Serverless MCP Servers

aws-samples

Sample implementations of AI Agents and MCP Servers running on AWS Serverless compute

239

Run Model Context Protocol (MCP) servers with AWS Lambda

awslabs

Run existing Model Context Protocol (MCP) stdio-based servers in AWS Lambda functions

373

🐋 Docker MCP server

ckreiling

MCP server for Docker

726

AWS Model Context Protocol (MCP) Server

alexei-led

A lightweight service that enables AI assistants to execute AWS CLI commands (in safe containerized environment) through the Model Context Protocol (MCP). Bridges Claude, Cursor, and other MCP-aware AI tools with AWS CLI for enhanced cloud infrastructure management.

184