DeepImage for AI agents
DeepImage upscales and enhances images with AI, letting a team improve photo quality or generate variations without any manual editing work. 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 DeepImage.
Upscale an image
Process an image asynchronously to upscale its resolution before it gets published.
Check a processing job's result
Check a processing job's result once its image has finished being enhanced.
Confirm before deleting a job
Confirm before deleting a job, since its processed image result is removed with it.
5 DeepImage actions, graded by risk.
Every DeepImage 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.
- deepimage.get_job_resultGet Job Result
- deepimage.get_account_infoGet Account Information
write
2Create and change things. Allow, or ask the user first.
- deepimage.process_image_syncProcess Image Synchronously
- deepimage.process_image_asyncProcess Image Async
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- deepimage.delete_jobDelete Job
DeepImage in three steps.
- 01Your users connect DeepImageThey add their DeepImage api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “process Image Synchronously” can wait for the user, and “delete Job” can be denied outright.
- 03Any agent can actYour agent calls DeepImage through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('deepimage', { read: 'allow', write: 'ask', // process_image_sync destructive: 'deny', // delete_job }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How DeepImage connects.
Users add their DeepImage 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 DeepImage 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 DeepImage from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
DeepImage and Arc0, answered.
Can I use DeepImage with Claude, ChatGPT or Cursor?
Yes. Connect DeepImage 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 DeepImage actions you allow.
How do users connect DeepImage?
Users add their DeepImage 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 DeepImage actions can my agent take?
5 in total: 2 read, 2 write and 1 destructive, such as “process Image Synchronously”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in DeepImage?
Yes. Actions like “delete Job” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call DeepImage too?
Yes. The same DeepImage connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug DeepImage into your agent.
Your users connect DeepImage once, under your brand. Your agent gets 5 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan