How do I run this MCP server locally?
Clone the repo, install dependencies, and run `npx nx dev remote-mcp-server`. The server will be available at `http://localhost:8787/`.
@Workman
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-workman": {
"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。
A template for deploying a remote MCP (Model Context Protocol) server on Cloudflare Workers with OAuth login. It provides a fully functional MCP server that can be accessed remotely by MCP clients such as Claude Desktop.
Clone the repository, install dependencies, and run locally with npx nx dev remote-mcp-server. Connect using the MCP Inspector with SSE transport, then deploy to Cloudflare Workers using npm run deploy. Configure Claude Desktop by pointing its configuration to the local or remote SSE endpoint via the mcp-remote proxy command.
npm run deployClone the repo, install dependencies, and run `npx nx dev remote-mcp-server`. The server will be available at `http://localhost:8787/`.
Add an entry to Claude Desktop's config file pointing to the SSE URL using the `mcp-remote` command, such as `npx mcp-remote http://localhost:8787/sse` for local or a workers.dev URL for remote.
Create an OAuth KV namespace with `npx wrangler kv namespace create OAUTH_KV`, add the namespace ID to `wrangler.jsonc`, then run `npm run deploy`.
The server uses SSE (Server-Sent Events) as its transport protocol.
OAuth state is stored in a Cloudflare KV namespace called `OAUTH_KV`. Local credentials can be cleared by deleting the `~/.mcp-auth` directory.
Deploy and manage SnapDeploy apps (Docker containers on AWS) from Claude Code, Cursor, Codex or Gemini CLI: builds, logs, env vars, add-ons, domains.
MCP server for Docker
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
MCP Server for kubernetes management commands
Connect Supabase to your AI assistants
コメント