Apiframe for AI agents
Apiframe is a single API for generating and managing AI images, video, and music across multiple models, used by developers building creative and generative apps. 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 Apiframe.
Generate an image from a prompt
Create an image using a chosen AI model and a written text prompt.
Check the status of a generation job
Look up a job to see whether an image or video render has finished.
Review account usage before a large job
Check account details before submitting a large music or video generation batch.
7 Apiframe actions, graded by risk.
Every Apiframe action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
4Look things up. Allowed by default.
- apiframe.get_jobGet Job
- apiframe.list_jobsList Jobs
- apiframe.get_accountGet Account
- apiframe.list_modelsList Models
write
3Create and change things. Allow, or ask the user first.
- apiframe.generate_imageGenerate Image
- apiframe.generate_musicGenerate Music
- apiframe.generate_videoGenerate Video
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Apiframe in three steps.
- 01Your users connect ApiframeThey add their Apiframe api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “generate Image” can wait for the user to approve.
- 03Any agent can actYour agent calls Apiframe through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('apiframe', { read: 'allow', write: 'ask', // generate_image destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Apiframe connects.
Users add their Apiframe 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 Apiframe 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 Apiframe from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Apiframe and Arc0, answered.
Can I use Apiframe with Claude, ChatGPT or Cursor?
Yes. Connect Apiframe 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 Apiframe actions you allow.
How do users connect Apiframe?
Users add their Apiframe 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 Apiframe actions can my agent take?
7 in total: 4 read, 3 write and 0 destructive, such as “generate Image”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Apiframe?
Yes. Allow read actions and deny writes in the Apiframe policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Apiframe too?
Yes. The same Apiframe connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Apiframe into your agent.
Your users connect Apiframe 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