All Images AI for AI agents
All Images AI is an image generation and management service that produces and organizes AI-generated images through an API. Developers use it to automate image creation for products and content. 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 All Images AI.
Check credits balance
Look up how many image generation credits remain before starting a new batch.
List automated image generations
Review the images generated automatically by the account's configured workflows before deciding what to publish.
Delete image generations
Remove a batch of generated images from the account, a destructive action worth confirming before it runs.
7 All Images AI actions, graded by risk.
Every All Images AI action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
5Look things up. Allowed by default.
- all_images_ai.get_creditsGet Credits Balance
- all_images_ai.get_webhookGet Webhook
- all_images_ai.list_automated_imagesList Automated Images
- all_images_ai.list_downloaded_imagesList Downloaded Images
- all_images_ai.check_api_keyCheck API Key
write
1Create and change things. Allow, or ask the user first.
- all_images_ai.create_webhook_endpointCreate webhook endpoint
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- all_images_ai.delete_image_generationsDelete Image Generations
All Images AI in three steps.
- 01Your users connect All Images AIThey add their All Images AI api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create webhook endpoint” can wait for the user, and “delete Image Generations” can be denied outright.
- 03Any agent can actYour agent calls All Images AI through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('all_images_ai', { read: 'allow', write: 'ask', // create_webhook_endpoint destructive: 'deny', // delete_image_generations }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How All Images AI connects.
Users add their All Images AI 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 All Images AI 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 All Images AI from any agent.
All Images AI and Arc0, answered.
Can I use All Images AI with Claude, ChatGPT or Cursor?
Yes. Connect All Images AI 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 All Images AI actions you allow.
How do users connect All Images AI?
Users add their All Images AI 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 All Images AI actions can my agent take?
7 in total: 5 read, 1 write and 1 destructive, such as “create webhook endpoint”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in All Images AI?
Yes. Actions like “delete Image Generations” 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 All Images AI too?
Yes. The same All Images AI connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug All Images AI into your agent.
Your users connect All Images AI once, under your brand. Your agent gets 7 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan