SlidesGPT for AI agents
SlidesGPT generates slide decks from a text prompt and exports them as ready-to-edit PowerPoint files, skipping the blank-slide starting point. 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 SlidesGPT.
Draft a deck from a prompt
Create a slide deck from a written prompt, producing a first draft outline and content for a presentation.
Apply a theme before sharing
Apply a visual theme to a generated deck so it matches brand colors before it goes out for review.
Regenerate a deck for feedback
Create a revised version of a deck after feedback, keeping the original draft available for comparison.
2 SlidesGPT actions, graded by risk.
Every SlidesGPT 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
2Create and change things. Allow, or ask the user first.
- slidesgpt.create_slidesCreate slides
- slidesgpt.apply_themeApply theme
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
SlidesGPT in three steps.
- 01Your users connect SlidesGPTThey add their SlidesGPT no auth on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “create slides” can wait for the user to approve.
- 03Any agent can actYour agent calls SlidesGPT through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('slidesgpt', { read: 'allow', write: 'ask', // create_slides destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How SlidesGPT connects.
SlidesGPT needs no credentials. Arc0 still applies your policies and records every call, so public tools get the same controls as private ones.
The same SlidesGPT 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
- No auth
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use SlidesGPT from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
SlidesGPT and Arc0, answered.
Can I use SlidesGPT with Claude, ChatGPT or Cursor?
Yes. Connect SlidesGPT 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 SlidesGPT actions you allow.
How do users connect SlidesGPT?
SlidesGPT needs no credentials. Arc0 still applies your policies and records every call, so public tools get the same controls as private ones.
Which SlidesGPT actions can my agent take?
2 in total: 0 read, 2 write and 0 destructive, such as “create slides”. Your policies decide which of them each agent may call.
Can I make my agent read-only in SlidesGPT?
Yes. Allow read actions and deny writes in the SlidesGPT policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call SlidesGPT too?
Yes. The same SlidesGPT connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug SlidesGPT into your agent.
Your users connect SlidesGPT once, under your brand. Your agent gets 2 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan