Groq MCP Server

Name: Groq MCP Server
Author: groq

@groq

リポジトリ

Groq MCP Server について

Groq MCP server

#managed-by-terraform

基本情報

カテゴリ

その他

ライセンス

MIT

ランタイム

python

トランスポート

stdio

公開者

groq

設定

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": {
    "groq-mcp-server": {
      "command": "uv",
      "args": [
        "venv"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

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。

概要

What is Groq MCP Server?

A Model Context Protocol (MCP) server that provides access to Groq’s lightning-fast model inference, including chat, vision, text-to-speech, speech-to-text, batch processing, and agentic tools. It is designed for developers using MCP clients like Claude Desktop to integrate Groq’s API capabilities directly into their workflows.

How to use Groq MCP Server?

Requires a free Groq API key and Python with uv (or pip). For Claude Desktop, add the server configuration to claude_desktop_config.json using uvx groq-mcp and your API key. For other clients, install the package and run groq-mcp-config to generate configuration. Optional BASE_OUTPUT_PATH environment variable sets where generated files are saved.

Key features of Groq MCP Server

Ultra-fast LLM inference with Groq models
Vision – image analysis and understanding
Text-to-speech (TTS) – natural speech synthesis
Speech-to-text (STT) – transcription and translation
Batch processing – process large workloads efficiently
Agentic tool usage (compound-beta) for web search, code generation, and API calls

Use cases of Groq MCP Server

Perform agentic tasks combining web search, code execution, and data retrieval
Analyze images and extract structured information (e.g., JSON)
Convert text to speech or transcribe audio files in multiple languages
Process high-volume batch prompts via JSONLines files
Build applications with full access to Groq’s documentation and models

FAQ from Groq MCP Server

What prerequisites are needed to run Groq MCP Server?

A Groq API key (free from console.groq.com), Python, and either uv or pip for installation. For Claude Desktop, you need the Developer Mode enabled on Windows.

How do I install the server for Claude Desktop?

Add the configuration shown in the README to claude_desktop_config.json using uvx groq-mcp and set the GROQ_API_KEY environment variable. On macOS, a setup script can install it automatically.

What client applications are supported?

Works with any MCP client, including Claude Desktop, Cursor, and Windsurf. Installation instructions differ; for non-Claude clients use groq-mcp-config to generate the config.

Where can I find server logs?

Logs are stored at ~/Library/Logs/Claude/groq-mcp.log on macOS and %APPDATA%\Claude\logs\groq-mcp.log on Windows.

Can I run the server from source?

Yes. Clone the repository, run ./scripts/setup.sh (or manually create a virtual environment and install dependencies), then use mcp install server.py to register the server.