# GroqCloud — how to use (mcp.ai)

Connect your GroqCloud account and use 7 tools for AI models straight from your AI agent. Connect with your own API key. GroqCloud provides high-performance AI inference services, enabling developers to deploy and manage AI models efficiently.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_groqcloud?ms=1787293440000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `groqcloud_create_audio_transcription`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/groqcloud`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/groqcloud/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/groqcloud/create/audio/transcription` — Tool to transcribe audio into text in the same language as the audio. Use when you need to convert speech to text while preserving the original language. Supports multiple formats including mp3, mp4, 
  - body: { file: object, model?: string, prompt?: string, language?: string, temperature?: number, response_format?: string, timestamp_granularities?: string[] }
- `POST https://api.mcp.ai/api/groqcloud/create/response` — Tool to create a model response for the given input. Beta endpoint with simplified interface compared to chat completions. Use when you need a streamlined API for generating model responses.
  - body: { text?: object, user?: string, input: string|object[], model: string, store?: boolean, tools?: object[], top_p?: number, stream?: boolean, metadata?: object, reasoning?: object, truncation?: string, temperature?: number, tool_choice?: string|object, instructions?: string, service_tier?: string, max_output_tokens?: integer, parallel_tool_calls?: boolean }
- `POST https://api.mcp.ai/api/groqcloud/groq/create/audio/translation` — Tool to translate an audio file into English text. Use when you have a non-English recording and need an accurate English transcript. Use after confirming the file path.
  - body: { file: object, model?: string, prompt?: string, temperature?: number, response_format?: string }
- `POST https://api.mcp.ai/api/groqcloud/groq/create/chat/completion` — Tool to generate a chat-based completion for a conversation. Use when you have a list of prior messages and need the model's next reply. Response completion text is at choices[0].message.content in th
  - body: { n?: integer, stop?: string|string[], user?: string, model: string, top_p?: number, messages: object[], temperature?: number, max_completion_tokens?: integer }
- `POST https://api.mcp.ai/api/groqcloud/groq/retrieve/model` — Tool to retrieve detailed information about a specific model. Use after listing models when you need metadata for a chosen model. Returned metadata may change as models update; do not cache.
  - body: { model: string }
- `POST https://api.mcp.ai/api/groqcloud/list/models` — Tool to list all available models and their metadata. Always call this to retrieve current model IDs rather than using hard-coded or cached identifiers, as deprecated names cause failures in GROQCLOUD
- `POST https://api.mcp.ai/api/groqcloud/list/voices` — Tool to retrieve available TTS voices for Groq PlayAI models. Use when you need to discover voice options before calling text-to-speech. Note: static list maintained manually; no live endpoint exists.

## Example prompts
- "What can I do in GroqCloud?"
- "Show me a summary of my GroqCloud account"

## More
- Page: https://mcp.ai/groqcloud
- Agent spec (llms.txt): https://mcp.ai/groqcloud/llms.txt
- Postman collection: https://mcp.ai/groqcloud/postman.json