Dreamstudio for AI agents
DreamStudio is Stability AI's interface for generating and editing images with AI, built for creators producing visual content from prompts. 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 Dreamstudio.
Generate an image from a prompt
Generate a new image from a text prompt when a user needs visual content for a project.
Edit an existing image
Generate a variation of an uploaded image based on new instructions from the user.
Check credit balance first
Read the account's balance before running a generation job that consumes credits.
5 Dreamstudio actions, graded by risk.
Every Dreamstudio action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
1Look things up. Allowed by default.
- dreamstudio.list_enginesList Engines
write
4Create and change things. Allow, or ask the user first.
- dreamstudio.user_accountUser Account
- dreamstudio.user_balanceDreamStudio User Balance
- dreamstudio.generate_image_from_textGenerate Image from Text
- dreamstudio.generate_image_from_imageGenerate Image from Image
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Dreamstudio in three steps.
- 01Your users connect DreamstudioThey add their Dreamstudio api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “user Account” can wait for the user to approve.
- 03Any agent can actYour agent calls Dreamstudio through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('dreamstudio', { read: 'allow', write: 'ask', // user_account destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Dreamstudio connects.
Users add their Dreamstudio 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 Dreamstudio 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 Dreamstudio from any agent.
Dreamstudio and Arc0, answered.
Can I use Dreamstudio with Claude, ChatGPT or Cursor?
Yes. Connect Dreamstudio 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 Dreamstudio actions you allow.
How do users connect Dreamstudio?
Users add their Dreamstudio 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 Dreamstudio actions can my agent take?
5 in total: 1 read, 4 write and 0 destructive, such as “user Account”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Dreamstudio?
Yes. Allow read actions and deny writes in the Dreamstudio policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Dreamstudio too?
Yes. The same Dreamstudio connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Dreamstudio into your agent.
Your users connect Dreamstudio 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