Imagior for AI agents
Imagior is an AI-powered image generation tool that creates and customizes images from templates via API. Design and marketing teams use it to produce this asset without a manual editing pass. 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 Imagior.
Browse design templates
List available design templates to pick a starting point for a new campaign asset.
Check account details
Check account details and plan limits before generating a large batch of images.
Confirm a template before reuse
Review a template's layout, read-only, before it is reused across multiple campaigns.
2 Imagior actions, graded by risk.
Every Imagior 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.
- imagior.get_accountGet account details
- imagior.list_templatesList design templates
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Imagior in three steps.
- 01Your users connect ImagiorThey add their Imagior api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls Imagior through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('imagior', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Imagior connects.
Users add their Imagior 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 Imagior 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 Imagior from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Imagior and Arc0, answered.
Can I use Imagior with Claude, ChatGPT or Cursor?
Yes. Connect Imagior 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 Imagior actions you allow.
How do users connect Imagior?
Users add their Imagior 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 Imagior actions can my agent take?
2 in total: 2 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Imagior?
Yes. Allow read actions and deny writes in the Imagior policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Imagior too?
Yes. The same Imagior connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Imagior into your agent.
Your users connect Imagior once, under your brand. Your agent gets 2 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan