What is Flato?
Flato is an AI Presentation Canvas powered by a native-canvas runtime for AI agents and human editors. It keeps presentations editable as structured canvas projects instead of one-shot generated files.
Create Presentations with AI Agents on an Editable Canvas
Flato gives AI agents and human editors a native presentation canvas to continuously create, edit, polish, animate, and export the same deck from rough draft to ready-to-present.
Please use desktop for the full Flato canvas experience.
Follow Flato on XThe Native Presentation Canvas for AI Agents
A native-canvas runtime keeps every presentation structured, editable, and ready for the next round of refinement.
Take Control Together on the Canvas
Flato Copilot works inside the editor with canvas context, helping shape layout, text, timing, and visual relationships while every element stays editable.
Layouts, Motion, and Video — One AI Design System
Create presentation systems that combine narrative, layout, visuals, charts, motion, and export in one editable native-canvas workflow.
Real-Time AI Design Collaboration
Human editors can review, rewrite, restyle, animate, present, export, and keep improving the same project after AI creates the first draft.
Flato MCP: Connect Your Agent to the Canvas
Use Flato MCP to let Codex, Claude Code, Cursor, and other agent clients work directly with editable Flato presentation projects.
GitHub package sologovision/flato-design-mcp
Please read this Flato MCP guide, install Flato MCP, trigger OAuth authorization when needed, guide me through the browser confirmation, verify the connection with flato_whoami, then follow the agent workflow in the guide. Important Codex App rule: after adding flato-editor or completing codex mcp login, the current Codex conversation may not hot-load newly added MCP tools. If flato_* tools are unavailable in this same conversation, stop and ask me to open a new Codex conversation or restart Codex App; do not inspect local OAuth/token stores or manually extract bearer tokens. When a project returns waiting_for_live_editor_bridge or needs_open_editor, have the MCP host/client open editorUrl automatically when supported, and only ask me to open editorUrl if the host cannot open URLs. Markdown guide: https://www.flato.ai/docs/mcp.md Endpoint
https://api.flato.ai/api/mcp/editor Claude Code
claude mcp add --transport http flato https://api.flato.ai/api/mcp/editor Codex
[mcp_servers.flato-editor]
url = "https://api.flato.ai/api/mcp/editor"
tool_timeout_sec = 120 Cursor
{
"mcpServers": {
"flato": {
"type": "http",
"url": "https://api.flato.ai/api/mcp/editor"
}
}
}Get Inspirations from Flato Starters
Explore designs created in Flato and pick one to get started.
1 / 2
1 / 2
1 / 2
Flato FAQ
Short answers about Flato, MCP, Credits, subscriptions, and native presentation canvas workflows.
What can Flato do beyond PowerPoint or Google Slides?
Programmable AI design runtime beyond traditional slide editors. Giving AI control over the full canvas, including text, styles, layout, images, charts, vector elements, and visual structure; Built-in image search across multiple sources, vector element generation, programmable animation, programmable interaction, and programmable charts; Creating richer editable design experiences than traditional slide tools.
Why use Flato MCP?
Connecting agent clients such as Claude Code, Codex, and Cursor to Flato; Letting agent clients create, inspect, and update the same live editable project; Continuing work from an existing editor URL or, when supported, turning a share link into an editable project copy. Instead of producing disconnected files, an agent client can keep working in the same live canvas while human editors keep control in the Flato editor.
Which agents does Flato MCP support?
Connecting agent clients such as Claude Code, Codex, and Cursor to Flato. It also supports other agent clients that can connect to a Streamable HTTP MCP server with OAuth authorization.
Can an agent continue editing an existing Flato project?
Yes. Letting agent clients create, inspect, and update the same live editable project. Continuing work from an existing editor URL or, when supported, turning a share link into an editable project copy.
Can an agent work from a shared Flato design?
Yes. When supported, Flato MCP can turn a Flato share link into an editable project copy in the authorized user's account, then continue work from that copied project.
Does using Flato MCP consume Flato Credits for local agent tokens?
No. Local agent tokens used through Flato MCP are not charged as Flato Credits; those costs are billed by the agent or AI service provider.
When are Flato Credits consumed?
Flato Credits are consumed only by Flato-side AI generation or media-processing features; manual canvas edits such as text changes, layout adjustments, or moving elements do not consume Credits.
Do I need a subscription to use Flato features?
Some Flato features require an active subscription, including MP4/MPEG-4 video export, vectorizer, and video generation; feature availability follows the current platform rules.
What can I edit manually in the Flato editor?
Dragging, moving, and resizing content; editing text; cropping images; changing canvas size and overall styles; Inserting text, images, and video, including dragging local images directly onto the canvas; Exporting selected elements or blocks, single pages, or complete multi-page projects as bitmap images, PDFs, or MP4/MPEG-4 video, and sharing links that can be edited further or played online
Create your next presentation on the AI-native canvas.
Start with a draft, connect your agent, and keep refining until the presentation is ready.