Contentdrips for AI agents
Contentdrips generates branded graphics and carousels from templates, letting a marketing team turn text into on-brand visuals 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 Contentdrips.
Start a carousel render
Start rendering a carousel from a template and a set of content slides.
Generate an AI-assisted carousel
Generate a carousel using AI to fill in a template's layout and copy.
Check a render job's status
Check a carousel render job's status before downloading the finished graphic file.
4 Contentdrips actions, graded by risk.
Every Contentdrips 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.
- contentdrips.get_render_jobGet Render Job
write
3Create and change things. Allow, or ask the user first.
- contentdrips.start_graphic_renderStart Graphic Render
- contentdrips.start_carousel_renderStart Carousel Render
- contentdrips.start_ai_carousel_renderStart AI Carousel Render
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Contentdrips in three steps.
- 01Your users connect ContentdripsThey add their Contentdrips api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “start Graphic Render” can wait for the user to approve.
- 03Any agent can actYour agent calls Contentdrips through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('contentdrips', { read: 'allow', write: 'ask', // start_graphic_render destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Contentdrips connects.
Users add their Contentdrips 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 Contentdrips 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 Contentdrips from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Contentdrips and Arc0, answered.
Can I use Contentdrips with Claude, ChatGPT or Cursor?
Yes. Connect Contentdrips 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 Contentdrips actions you allow.
How do users connect Contentdrips?
Users add their Contentdrips 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 Contentdrips actions can my agent take?
4 in total: 1 read, 3 write and 0 destructive, such as “start Graphic Render”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Contentdrips?
Yes. Allow read actions and deny writes in the Contentdrips policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Contentdrips too?
Yes. The same Contentdrips connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Contentdrips into your agent.
Your users connect Contentdrips once, under your brand. Your agent gets 4 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan