AI-agent editing with WebMCP

WebDecks, WebDocs and WebSheets speak WebMCP — the Web Model Context Protocol — so an AI agent can drive your real documents the same way you do. Point ChatGPT's browser (Operator-style) mode, or any WebMCP-capable client, at the app and it can open a file, read its contents, make edits and export the result. Everything runs in your browser: your files never leave your device.

What WebMCP support means

The Web Model Context Protocol lets a web page publish a set of tools that an AI agent can call directly through the browser, via the emerging navigator.modelContext API. WebDecks registers its editing tools with the browser, so a connected agent sees a structured, typed surface — not a screenshot to guess at — and acts on the actual document model.

Because the agent works through the same engine as the UI, its edits are real edits: it reads the true text, shapes and structure of your file, changes them, and can export the finished PPTX, DOCX, XLSX or PDF. There is no lossy round-trip and nothing is uploaded to a server — the model runs on your document, locally.

Two ways to connect an agent

In-app on the apps themselves. Open WebDecks, WebDocs or WebSheets and the page registers its WebMCP tools with your browser through navigator.modelContext. An agent running in that browser — ChatGPT's browser/Operator-style mode, or any WebMCP client — can then read and edit whatever document you have open.

The standalone /mcp/ endpoint. A dedicated, self-contained WebMCP page lives at /mcp/ for agents that want to connect to the tool surface directly without the full editor chrome around it. It exposes the same read, edit and export tools over WebMCP.

The tool surface: read, edit, export

Read. Agents can inspect the document model — slide and page structure, text runs, tables, cell values and formulas, shapes and images — as structured data, so they can answer questions about a file or plan an edit precisely.

Edit. Agents can make real changes: insert and rewrite text, fix typos, restyle and format, add or move shapes, update table and spreadsheet cells, and reorganize content — every change applied through the same engine the editor uses.

Export. When the work is done, an agent can export the result to the native format (PPTX, DOCX, XLSX) or to PDF, exactly as the app's own File menu would.

AI editing, per app

On the roadmap: a remote MCP connector

Today WebMCP support runs in the browser, next to your files. A remote HTTP/SSE MCP connector — so an agent or assistant can reach a WebDecks tool surface over the network as a hosted Model Context Protocol server — is on the roadmap.

Building on the engine

If you want to embed this document engine — and its AI-driveable surface — in your own product, the WebDecks SDK is a TypeScript API over the same browser-native engine that powers the apps.

Read the SDK docs

The SDK is free to try. Production use — or shipping on any other origin — needs a commercial license with an unlocked, origin-bound build.