v146 · Origin Trial · AI Agents
WebMCP
A browser-native implementation of the Model Context Protocol — sites register structured tools that AI agents can discover and invoke directly, without scraping HTML or relying on hidden APIs.
navigator.modelContext. These demos simulate the API surface with mock implementations so you can explore the concept before registering for the trial.
concepts
-
Tool Registry Explorer
Register MCP tools on a page using the
navigator.modelContextAPI, then inspect what an AI agent would discover. Define tool schemas, input parameters, and handler functions — live, in the browser. -
Agent Handshake Simulator
Watch the full agent–page interaction unfold: a simulated AI agent discovers your registered tools, selects the right one for a task, sends a structured call, and receives a response. Step through each phase with annotations.
-
Tool call replay
Type a natural-language prompt and watch the page's tool registry pick a match, extract arguments, and dispatch. Includes scripted prompts plus a freestyle box for ad-hoc experiments.
-
MCP Tool Tester
Select a tool from a simulated MCP server registry, fill in parameters, and invoke it. The JSON-RPC trace panel shows the exact
tools/callrequest a model sends and theresultresponse the server returns.
why it shipped
AI agents interacting with the web today face a fundamental mismatch: websites are designed for human eyes — HTML, visual layouts, implicit affordances. Agents scrape, guess at selectors, and break on every redesign. The Model Context Protocol (MCP) addresses this by letting sites expose machine-readable capability descriptions: here is what I can do, here is how to call it, here is the schema of the result. WebMCP brings MCP natively into the browser via navigator.modelContext, so any installed AI (Gemini in Chrome, a local LLM, an agentic extension) can discover and invoke tools without HTTP calls to a separate server, without scraping, and with full user-consent visibility. The origin trial starting in Chrome 149 lets developers experiment with the API and give feedback before it becomes a baseline feature.