What does mcp-server-server do?
It takes a stdio MCP server command and exposes it as a websocket server, so clients can connect over the network instead of managing subprocesses.
@MCP-Mirror
基本情報
Mirror of
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": {
"rgarcia_mcp-server-server": {
"command": "bun",
"args": [
"run",
"mcp-server",
"-p",
"3001",
"--",
"npx",
"-y",
"@modelcontextprotocol/server-puppeteer@latest"
]
}
}
}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。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
A proof-of-concept MCP server wrapper that converts stdio-based MCP servers into websocket servers, allowing programmatic interaction over the network without spawning subprocesses.
Run the wrapper with bun run mcp-server -p <port> -- <mcp-server-command> (e.g., bun run mcp-server -p 3001 -- npx -y @modelcontextprotocol/server-puppeteer@latest). Then connect using WebSocketClientTransport from the MCP SDK.
It takes a stdio MCP server command and exposes it as a websocket server, so clients can connect over the network instead of managing subprocesses.
WebSocket transport. Clients connect using `WebSocketClientTransport` from the MCP SDK.
Bun is required to run the wrapper. The client side uses the MCP SDK (`@modelcontextprotocol/sdk`) and Node.js/Bun.
No, this is a proof of concept. Multi-user configuration support (step 3) is marked as TODO.
Use the MCP Client with `WebSocketClientTransport` pointing to the websocket URL (e.g., `ws://localhost:3001`).

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
A curated list of references for MLOps
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov
コメント