Browse
→ Code & Dev
→ Chrome WebMCP
Chrome WebMCP
WebMCP from Google Chrome, available in early preview for Chrome Canary. A proposed web standard that turns any web page into a structured MCP-compatible tool for AI agents. Provides both a Declarative API for standard HTML form actions and an Imperative API for complex dynamic interactions via JavaScript. Instead of screenshot-analyze-click loops, AI agents call declared tools directly with typed parameters. Backed by Booking.com, Expedia, Instacart, Intuit, Shopify, and Redfin. Native browser support expected across Chrome and Edge in H2 2026.
MCP verified
Integration
| Transport | http |
| Auth | none |
| Endpoint | Chrome WebMCP |
Use Cases
| 01 | Enable AI agents to interact with websites through structured tool calls instead of slow screenshot-analyze-click loops by declaring page actions as MCP-compatible tools |
| 02 | Build agent-ready web applications using the Declarative API for HTML form actions and the Imperative API for complex JavaScript interactions that AI agents can invoke directly |
| 03 | Make e-commerce, travel, and service websites natively accessible to AI agents like Claude and ChatGPT through Google's WebMCP standard without building separate API integrations |
Tags
chrome google browser web-standard agent-ready forms automation web-interaction
Machine-readable: /api/servers.json
· JSON-LD schema embedded in <head>