How do I run the server locally?
Run `npx nx dev remote-mcp-server` and open http://localhost:8787/ in your browser.
@MFLS2023
基本情報
概要はまだありません
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"remote-mcp-server-mfls2023": {
"command": "npx",
"args": [
"nx",
"dev",
"remote-mcp-server"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。
Remote MCP Server on Cloudflare is a setup to run a remote MCP (Model Context Protocol) server on Cloudflare Workers with OAuth login. It is intended for developers who want to host an MCP server remotely and connect it to MCP clients such as Claude Desktop.
Clone the repository, install dependencies, and run locally with npx nx dev remote-mcp-server. To deploy, create a KV namespace (npx wrangler kv namespace create OAUTH_KV), add its ID to wrangler.jsonc, then run npm run deploy. Connect clients via SSE URL (e.g., worker-name.account-name.workers.dev/sse) using npx @modelcontextprotocol/inspector for testing or npx mcp-remote <sse-url> for Claude Desktop.
Run `npx nx dev remote-mcp-server` and open http://localhost:8787/ in your browser.
Run `npx @modelcontextprotocol/inspector`, select SSE transport, enter `http://localhost:8787/sse` as the URL, click Connect, and log in with any email and password.
Add a configuration entry in Claude’s settings using `npx mcp-remote` with the SSE URL – `http://localhost:8787/sse` for local, or `https://worker-name.account-name.workers.dev/sse` for remote.
Create a KV namespace with `npx wrangler kv namespace create OAUTH_KV`, add the returned ID to `wrangler.jsonc`, then run `npm run deploy`.
Restart Claude, test connectivity
The official Webshare MCP server. Manage your proxies, usage, plans and billing from Claude, Cursor or any MCP client. Sign in with OAuth, no API key.
An MCP server for Azure DevOps

Your AI can finally reach the physical world. Kilo is an AI-first IoT platform for commercial and industrial operations, and this connector hands a live deployment to the AI client you already use. Not an export. Not a
A docker MCP Server (modelcontextprotocol)
コメント