Creatomate for AI agents
Creatomate generates videos, images, and GIFs from reusable templates through an API, letting a team automate content that would otherwise need editing software. 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 Creatomate.
Render a video from a template
Create a render from a template, swapping in new text or footage for a batch of videos.
Check a render's status
Check a render's status before downloading the finished video or image file.
Confirm before deleting a template
Confirm before deleting a template, since any scheduled render using it would fail.
7 Creatomate actions, graded by risk.
Every Creatomate action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
3Look things up. Allowed by default.
- creatomate.get_renderGet Render
- creatomate.get_templateGet Template
- creatomate.list_templatesList Templates
write
3Create and change things. Allow, or ask the user first.
- creatomate.create_renderCreate Render
- creatomate.create_templateCreate Template
- creatomate.update_templateUpdate Template
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- creatomate.delete_templateDelete Template
Creatomate in three steps.
- 01Your users connect CreatomateThey add their Creatomate api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Render” can wait for the user, and “delete Template” can be denied outright.
- 03Any agent can actYour agent calls Creatomate through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('creatomate', { read: 'allow', write: 'ask', // create_render destructive: 'deny', // delete_template }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Creatomate connects.
Users add their Creatomate 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 Creatomate 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 Creatomate from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Creatomate and Arc0, answered.
Can I use Creatomate with Claude, ChatGPT or Cursor?
Yes. Connect Creatomate 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 Creatomate actions you allow.
How do users connect Creatomate?
Users add their Creatomate 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 Creatomate actions can my agent take?
7 in total: 3 read, 3 write and 1 destructive, such as “create Render”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Creatomate?
Yes. Actions like “delete Template” 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 Creatomate too?
Yes. The same Creatomate connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Creatomate into your agent.
Your users connect Creatomate 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