Claid.ai for AI agents
Claid.ai edits images with AI, handling background removal, upscaling, and color correction so a team can prep product photos without a designer. 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 Claid.ai.
Remove an image's background
Remove the background from a product photo before placing it on a clean listing page.
Generate an AI background
Generate a new AI background for a product shot instead of a plain studio backdrop.
Check connected storage
Check which storage locations are connected before sending a batch of images for editing.
14 Claid.ai actions, graded by risk.
Every Claid.ai action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
0Look things up. Allowed by default.
- No read actions.
write
13Create and change things. Allow, or ask the user first.
- claid_ai.create_storageConnect New Storage
- claid_ai.smart_frameCLAID Smart Frame
- claid_ai.polish_imagePolish Image
- claid_ai.storage_listList Connected Storages
- claid_ai.image_ai_editImage AI Edit Async
- claid_ai.patch_storageUpdate Connected Storage
- claid_ai.storage_typesList Storage Types
- claid_ai.image_generateGenerate AI Images from Text Prompt
- claid_ai.image_edit_batchCLAID Image Edit Batch
- claid_ai.generative_resizeGenerative Resize (Outpaint)
- claid_ai.license_plate_blurCLAID License Plate Blur
- claid_ai.background_generateGenerate AI Backgrounds
- claid_ai.claid_storage_detailsGet Storage Details
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- claid_ai.background_removeCLAID Background Remove
Claid.ai in three steps.
- 01Your users connect Claid.aiThey add their Claid.ai api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “connect New Storage” can wait for the user, and “cLAID Background Remove” can be denied outright.
- 03Any agent can actYour agent calls Claid.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('claid_ai', { read: 'allow', write: 'ask', // create_storage destructive: 'deny', // background_remove }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Claid.ai connects.
Users add their Claid.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 Claid.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 Claid.ai from any agent.
Claid.ai and Arc0, answered.
Can I use Claid.ai with Claude, ChatGPT or Cursor?
Yes. Connect Claid.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 Claid.ai actions you allow.
How do users connect Claid.ai?
Users add their Claid.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 Claid.ai actions can my agent take?
14 in total: 0 read, 13 write and 1 destructive, such as “connect New Storage”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Claid.ai?
Yes. Actions like “cLAID Background Remove” 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 Claid.ai too?
Yes. The same Claid.ai connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Claid.ai into your agent.
Your users connect Claid.ai once, under your brand. Your agent gets 14 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan