0n3
MCP servers · ai

Groq MCP server

Ultra-fast AI inference — chat completions, embeddings, audio transcription. Hosted by 0n3: 3 endpoints your AI can call with your own Groq account, from Claude, ChatGPT, Cursor, Claude Code, Codex or Gemini CLI. One sign-in, one key per AI, a receipt for every call.

Connect GroqInstall into your AIWatch it work

3 endpoints3 categoriesauth: api_keyhosted

What your AI can do with Groq

Chat · Chat completions with Llama, Mixtral, Gemma1
Chat completionPOST /v1/chat/completions
Audio · Audio transcription via Whisper1
Create a transcriptionPOST /v1/audio/transcriptions
Models · List available models1
List modelsGET /v1/models

Install in three steps

  1. Create a free account at 0n3.app and connect Groq: paste a key or sign in through a door. It lands in your vault, encrypted.
  2. Open 0n3.app/install, pick your AI. A key is made for that AI alone; copy the line it gives you.
  3. Ask your AI: whoami. It answers with your connected services. Then ask it to chat completion in Groq.
Install (user scope — every project)
claude mcp add --transport http --scope user 0n3 https://0n3.app/mcp --header "Authorization: Bearer <your 0n token>"

Connect Groq to

Claude Code + GroqMCP server + skillClaude (desktop & claude.ai) + GroqconnectorChatGPT + Groqconnector · GPT actionCodex CLI + GroqMCP serverGemini CLI + GroqMCP serverCursor + GroqMCP serverVS Code (Copilot) + GroqMCP serverWindsurf + GroqMCP server

More ai MCP servers

Ollama8 endpointsElevenLabs8 endpointsReplicate8 endpointsDeepgram7 endpointsCohere6 endpointsStability AI6 endpointsOpenAI4 endpointsMistral3 endpoints

Questions

What can an AI do with the Groq MCP server?

3 things: chat, audio, models. Every call runs with your own Groq connection and lands on a receipt.

Do I need to run anything on my computer?

No. 0n3 is hosted. Connect Groq once, install 0n3 into your AI with one line, done.

Where does my Groq key go?

Into your 0n3 vault, encrypted, one record per connection. The AI never sees it.