Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-server-groq Summarize this Python function"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An official, ultra-fast Model Context Protocol (MCP) server enabling AI tools (Claude Desktop, Cursor, Antigravity) to route high-speed inference, fast completions, and code analysis to Groq's LLaMA 3.3 70B engine.
groq_fast_chat: Ultra-fast LLM completion using llama-3.3-70b-versatile.
groq_summarize_code: Instant code analysis, architectural breakdown, and bug checking.
Standard Stdio Interface: Fully compliant with the Anthropic Model Context Protocol specification.
Related MCP server: groq-compound-mcp-server
pip install mcp-server-groqSet your GROQ_API_KEY environment variable:
export GROQ_API_KEY="your-groq-api-key"$env:GROQ_API_KEY="your-groq-api-key"claude_desktop_config.json){
"mcpServers": {
"groq": {
"command": "python",
"args": ["-m", "mcp_server_groq"],
"env": {
"GROQ_API_KEY": "your-groq-api-key"
}
}
}
}MIT License. Created by Bhanu Kiran.
This server cannot be deployed
LLM chat, text tools, image generation, editing, batch image jobs, and asynchronous video generation
Connect AI assistants to your GitHub-hosted Obsidian vault to seamlessly access, search, and analy…
The OpenRouter MCP server plugs OpenRouter into the AI tools you already use. Once connected, your assistant can pull live OpenRouter data (models, prices, your credits, rankings, and docs) and send quick test messages, all without leaving your editor.
Code intelligence for coding agents: semantic, AST, graph, and full-text search. 279+ languages.
