Get started

Grok for AI agents

Grok is xAI's API platform for text, image, video, and voice generation, used by developers to add generative AI features to apps. 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.

Connect GrokSee the 8 actions ↓
AI and modelsAPI keyMCP + RESTx.ai
AUDIT LOG · GROKPOLICY: acme-support
09:41:07 · claude · u_8f2read
grok.list_models
List Models✓ allowed · 212ms
09:41:08 · claude · u_8f2read
grok.get_video
Get Video✓ allowed · 164ms
09:41:09 · claude · u_8f2write
grok.create_response
Create Response✓ approved · approved by user
EVERY GROK CALL, ON THE RECORD
01 · USE CASES

What agents do in Grok.

01

Generate a text response

Send a prompt to Grok and return a generated response for a chat or drafting task.

02

Generate an image from a prompt

Generate an illustrative image from a text description for a blog post or slide.

03

Check available models

List available models to pick the right one for a given task's cost and quality needs.

02 · ACTIONS

8 Grok actions, graded by risk.

Every Grok action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

4

Look things up. Allowed by default.

  • grok.get_video
    Get Video
  • grok.list_models
    List Models
  • grok.get_api_key_info
    Get API Key Info
  • grok.get_current_account
    Get Current Account

write

4

Create and change things. Allow, or ask the user first.

  • grok.create_response
    Create Response
  • grok.create_embeddings
    Create Embeddings
  • grok.generate_image
    Generate Image
  • grok.generate_video
    Generate Video

destructive

0

Delete, cancel or archive. Ask first, or deny outright.

  • No destructive actions.
03 · HOW IT WORKS

Grok in three steps.

  1. 01Your users connect GrokThey add their Grok api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “create Response” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Grok through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('grok', {
  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
04 · AUTH AND DATA

How Grok connects.

Users add their Grok 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 Grok 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
05 · WORKS WITH

Use Grok from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More ai and models apps.

Perplexity AI9 actionsAffinda119 actionsAgent Mail5 actionsAI/ML API30 actionsAivoov1 actionsAll Images AI7 actionsAltText.ai10 actionsAltTextLab2 actions
ALL AI AND MODELS APPS →
07 · FAQ

Grok and Arc0, answered.

Q01

Can I use Grok with Claude, ChatGPT or Cursor?

Yes. Connect Grok 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 Grok actions you allow.

Q02

How do users connect Grok?

Users add their Grok 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.

Q03

Which Grok actions can my agent take?

8 in total: 4 read, 4 write and 0 destructive, such as “create Response”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Grok?

Yes. Allow read actions and deny writes in the Grok policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Grok too?

Yes. The same Grok connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Grok into your agent.

Your users connect Grok once, under your brand. Your agent gets 8 actions behind your policies, with every call on the record.

Connect GrokBrowse all apps →

Free to build · MCP + REST · Audit log on every plan