ImageRouter for AI agents
ImageRouter generates images, video, and text through a unified API and lets developers discover and switch between models. 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 ImageRouter.
Generate an image from a prompt
Generate an image from a text prompt for a blog post header or ad creative.
Check remaining credits
Check the account's remaining credits before starting a large generation batch.
List available models
List available image and video models to choose the best fit for a task's budget.
8 ImageRouter actions, graded by risk.
Every ImageRouter action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
3Look things up. Allowed by default.
- imagerouter.get_modelGet Model
- imagerouter.get_creditsGet Credits
- imagerouter.list_modelsList Models
write
5Create and change things. Allow, or ask the user first.
- imagerouter.create_responseCreate Response
- imagerouter.create_chat_completionCreate Chat Completion
- imagerouter.edit_imageEdit Image
- imagerouter.generate_imageGenerate Image
- imagerouter.generate_videoGenerate Video
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
ImageRouter in three steps.
- 01Your users connect ImageRouterThey add their ImageRouter 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 ImageRouter through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('imagerouter', { 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 ImageRouter connects.
Users add their ImageRouter 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 ImageRouter 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 ImageRouter from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
ImageRouter and Arc0, answered.
Can I use ImageRouter with Claude, ChatGPT or Cursor?
Yes. Connect ImageRouter 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 ImageRouter actions you allow.
How do users connect ImageRouter?
Users add their ImageRouter 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 ImageRouter actions can my agent take?
8 in total: 3 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 ImageRouter?
Yes. Allow read actions and deny writes in the ImageRouter policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call ImageRouter too?
Yes. The same ImageRouter connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug ImageRouter into your agent.
Your users connect ImageRouter once, under your brand. Your agent gets 8 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan