How do I connect the MCP Inspector?
Start the inspector with `npx @modelcontextprotocol/inspector`, set Transport Type to SSE, enter `http://localhost:8787/sse` (or your remote URL), and log in with any email/password.
@Rev4nchist
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": {
"cloudflare-remote-mcp-server-rev4nchist": {
"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。
Remote MCP Server on Cloudflare is a reference implementation that deploys a Model Context Protocol (MCP) server on Cloudflare Workers with OAuth login. It demonstrates how to run a remote MCP server that communicates over SSE (Server-Sent Events) and can be connected to MCP clients such as the MCP Inspector or Claude Desktop.
Clone the repository, install dependencies with npm install, and run locally using npx nx dev remote-mcp-server. Connect via the MCP Inspector by selecting SSE transport and entering http://localhost:8787/sse. For Claude Desktop, configure mcpServers with the mcp-remote command pointing to the SSE URL. Deploy to Cloudflare with npm run deploy after setting up an OAuth KV namespace in wrangler.jsonc.
Start the inspector with `npx @modelcontextprotocol/inspector`, set Transport Type to SSE, enter `http://localhost:8787/sse` (or your remote URL), and log in with any email/password.
Edit Claude Desktop’s config file and add an entry using `mcp-remote` with the command `npx` and args `["mcp-remote", "http://localhost:8787/sse"]` (or your remote URL). Restart Claude; a browser window will open for login.
Create a KV namespace with `npx wrangler kv namespace create OAUTH_KV`, add the namespace ID to `wrangler.jsonc`, then run `npm run deploy`.
Try restarting Claude, or connect directly via `npx mcp-remote http://localhost:8787/sse`. If needed, clear cached auth files with `rm -rf ~/.mcp-auth`.
The server communicates over SSE (Server-Sent Events). Clients connect to the `/sse` endpoint of the server URL.

Build and run websites, APIs, automations, and admin tools from chat. Your agent creates the data, logic, pages, and scheduled jobs; Tessryx hosts them on your own domain. No code generated, nothing to deploy.
Model Context Protocol (MCP) server for Kubernetes and OpenShift
A docker MCP Server (modelcontextprotocol)
MCP server connecting to Kubernetes
Open source MCP Servers for AWS
评论