GroqCloud for AI agents
GroqCloud provides fast AI inference for chat, transcription, and translation, letting developers run models with low latency. Teams building AI products use it to add this capability without training or hosting their own model. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in GroqCloud.
Run a chat completion
Send a prompt through GroqCloud's chat completion endpoint for a fast, low-latency response.
Transcribe an audio clip
Submit an audio file for transcription and return the resulting text.
List available models
List the models currently available on the account before choosing one for a task.
7 GroqCloud actions, graded by risk.
Every GroqCloud action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
2Look things up. Allowed by default.
- groqcloud.list_modelsList Models
- groqcloud.list_voicesList TTS Voices
write
5Create and change things. Allow, or ask the user first.
- groqcloud.create_responseCreate Response
- groqcloud.create_audio_transcriptionCreate Audio Transcription
- groqcloud.groq_retrieve_modelRetrieve Model
- groqcloud.groq_create_chat_completionCreate Chat Completion
- groqcloud.groq_create_audio_translationCreate Audio Translation
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
GroqCloud in three steps.
- 01Your users connect GroqCloudThey add their GroqCloud api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “create Response” can wait for the user to approve.
- 03Any agent can actYour agent calls GroqCloud through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('groqcloud', { read: 'allow', write: 'ask', // create_response destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How GroqCloud connects.
Users add their GroqCloud api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same GroqCloud connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use GroqCloud from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
GroqCloud and Arc0, answered.
Can I use GroqCloud with Claude, ChatGPT or Cursor?
Yes. Connect GroqCloud to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the GroqCloud actions you allow.
How do users connect GroqCloud?
Users add their GroqCloud api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which GroqCloud actions can my agent take?
7 in total: 2 read, 5 write and 0 destructive, such as “create Response”. Your policies decide which of them each agent may call.
Can I make my agent read-only in GroqCloud?
Yes. Allow read actions and deny writes in the GroqCloud policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call GroqCloud too?
Yes. The same GroqCloud connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug GroqCloud into your agent.
Your users connect GroqCloud once, under your brand. Your agent gets 7 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan