What runtime or dependencies are required?
Node.js is needed to run the local development and deployment scripts (nx, wrangler). The server itself runs on Cloudflare Workers.
@LiTschii
基本信息
暂无概览
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-litschii": {
"command": "npx",
"args": [
"nx",
"dev",
"remote-mcp-server"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
A template for deploying a remote MCP (Model Context Protocol) server on Cloudflare Workers with OAuth login. It provides a complete local development setup, deployment instructions, and guidance for connecting MCP Inspector or Claude Desktop to the server over SSE.
Clone the repository, install dependencies with npm install, and run locally using npx nx dev remote-mcp-server (opens on http://localhost:8787/). Connect MCP Inspector or Claude Desktop by pointing them to the /sse endpoint, or deploy to Cloudflare with npm run deploy after creating an OAUTH_KV namespace.
mcp-remote proxyNode.js is needed to run the local development and deployment scripts (nx, wrangler). The server itself runs on Cloudflare Workers.
The server includes OAuth login. During local development, a mock login screen accepts any email and password. When deployed, proper OAuth flows apply.
OAuth tokens are stored in a Cloudflare KV namespace (`OAUTH_KV`) that you must create before deployment.
The server uses Server-Sent Events (SSE) — connect clients to the `/sse` endpoint.
No. To connect Claude Desktop, you must run a local proxy using `npx mcp-remote <server-url>/sse` as shown in the example configuration.
Find, price and rent GPUs on Lium from Claude, ChatGPT, Codex or any MCP client. Search live GPU availability and prices (H100, H200, B200, RTX 4090 and more), estimate provider earnings, and with Sign in with Lium or a
Deploy and manage SnapDeploy apps (Docker containers on AWS) from Claude Code, Cursor, Codex or Gemini CLI: builds, logs, env vars, add-ons, domains.
An MCP server for Azure DevOps
Open source MCP Servers for AWS
MCP server for Backblaze B2 Cloud Storage: a focused, safe 40-tool surface (17 native B2 SDK, 19 S3 data-plane, 4 analytics) for any MCP-compatible AI client, currently incubating in Backblaze-Labs
评论