Presenton for AI agents
Presenton generates and manages presentations through a cloud API, turning outlines into finished decks. Teams use it to produce slide decks quickly from source material. 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 Presenton.
Generate a presentation outline
Create a structured outline for a deck based on a topic or source document.
Check generation task status read-only
Poll an async presentation generation task to see if it has finished.
Export a finished presentation
Export a completed presentation to a file format ready to share or present.
8 Presenton actions, graded by risk.
Every Presenton 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.
- presenton.list_presentationsList Presentations
- presenton.list_smart_designsList Smart Designs
- presenton.get_async_task_statusGet Async Task Status
- presenton.list_standard_templatesList Standard Templates
- presenton.export_presentationExport Presentation
write
3Create and change things. Allow, or ask the user first.
- presenton.generate_outlineGenerate Outline
- presenton.upload_source_filesUpload Source Files
- presenton.generate_presentation_asyncGenerate Presentation Asynchronously
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Presenton in three steps.
- 01Your users connect PresentonThey add their Presenton api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “generate Outline” can wait for the user to approve.
- 03Any agent can actYour agent calls Presenton through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('presenton', { read: 'allow', write: 'ask', // generate_outline destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Presenton connects.
Users add their Presenton 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 Presenton 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 Presenton from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Presenton and Arc0, answered.
Can I use Presenton with Claude, ChatGPT or Cursor?
Yes. Connect Presenton 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 Presenton actions you allow.
How do users connect Presenton?
Users add their Presenton 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 Presenton actions can my agent take?
8 in total: 5 read, 3 write and 0 destructive, such as “generate Outline”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Presenton?
Yes. Allow read actions and deny writes in the Presenton policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Presenton too?
Yes. The same Presenton connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Presenton into your agent.
Your users connect Presenton once, under your brand. Your agent gets 8 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan