What tools does groq-compound-mcp-server expose?
It exposes two tools: `ask_with_realtime_information` and `ask_with_code_execution`.
@groq
基本信息
Groq Compound Beta MCP Server
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"groq-compound": {
"command": "npx",
"args": [
"-y",
"groq-compound-mcp-server"
],
"env": {
"GROQ_API_KEY": ""
}
}
}
}Ask a question requiring real-time information (e.g., news, current events) using a Groq model.
Ask questions that benefit from Python REPL interaction (e.g., for intermediate calculations or code execution).
It is a Model Context Protocol (MCP) server that provides tools for interacting with Groq models, including compound/meta models. It is designed for developers integrating Groq AI capabilities into MCP-compatible clients.
Install the package via npm install groq-compound-mcp-server, set the GROQ_API_KEY environment variable, and configure an MCP client (e.g., Claude Desktop) to launch the server using npx groq-compound-mcp-server. Alternatively, deploy on Vercel with optional Redis for SSE support.
ask_with_realtime_information and ask_with_code_execution.It exposes two tools: `ask_with_realtime_information` and `ask_with_code_execution`.
Node.js ≥ 18.0.0 and a Groq API key set in the `GROQ_API_KEY` environment variable.
Connect your Git repository to Vercel, set `GROQ_API_KEY` and optionally `REDIS_URL` environment variables, and deploy. The MCP endpoints will be available at `https://your-deployment-url.vercel.app/api/mcp`.
Yes, when deployed on Vercel, it supports SSE transport if a Redis instance (configured via `REDIS_URL`) is provided.
By default, it uses stdio transport, following the standard MCP server pattern.

Model Context Protocol Servers
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
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
Hindsight: Agent Memory That Learns
评论