The Web Model Context API is a W3C Community Group draft spec. It makes every browser tab a tool source — web pages register tools that AI agents can discover and call:
navigator.modelContext
├── .registerTool(tool) Register a tool for AI agents
├── .unregisterTool(name) Remove a tool
├── .provideContext(options) Set tools (replaces existing)
└── .clearContext() Remove all tools
MCP-b polyfills that API for all browsers today, and bridges it to the full Model Context Protocol — turning that tool source into a complete MCP server with prompts, resources, sampling, and transports.
Built by MCP-b. Not an official W3C or MCP project.
If you're running Chrome with --enable-experimental-web-platform-features, navigator.modelContext is already there. Just use it:
Add @mcp-b/webmcp-types (pnpm add -D @mcp-b/webmcp-types) for full input/output schema inference:
navigator.modelContext.registerTool({
name: 'add_todo',
description: 'Add a new todo item',
inputSchema: {
type: 'object',
properties: { title: { type: 'string' }, done: { type: 'boolean' } },
required: ['title'],
} as const, // ← args inferred: { title: string; done?: boolean }
outputSchema: { // ← optional — infers return type
type: 'object',
properties: { id: { type: 'number' }, title: { type: 'string' } },
required: ['id', 'title'],
} as const,
execute: async (args) => ({ id: Date.now(), title: args.title }),
});Want it to work in any browser without the Chrome flag? Add the polyfill — same API, same code:
import { initializeWebMCPPolyfill } from '@mcp-b/webmcp-polyfill'; // pnpm add @mcp-b/webmcp-polyfill
initializeWebMCPPolyfill(); // no-op if native support exists
navigator.modelContext.registerTool({
name: 'get_page_title',
description: 'Returns the current page title',
inputSchema: { type: 'object', properties: {} },
execute: async () => ({
content: [{ type: 'text', text: document.title }],
}),
});Or with React: pnpm add usewebmcp
import { useWebMCP } from 'usewebmcp';
function PageTitle() {
useWebMCP({
name: 'get_page_title',
description: 'Returns the current page title',
execute: async () => ({ title: document.title }),
});
// ...
}Need the full Model Context Protocol — prompts, resources, sampling, transports, interop with Claude Desktop / Cursor / any MCP client? Use @mcp-b/global:
import '@mcp-b/global'; // pnpm add @mcp-b/global
// Same registerTool API — now backed by a full MCP server
navigator.modelContext.registerTool({
name: 'add_todo',
description: 'Add a new todo item',
inputSchema: {
type: 'object',
properties: {
title: { type: 'string', description: 'Todo title' },
},
required: ['title'],
},
execute: async (args) => {
const todo = { id: Date.now(), ...args };
return { content: [{ type: 'text', text: JSON.stringify(todo) }] };
},
});Or as a script tag (zero build step):
<script src="https://unpkg.com/@mcp-b/global/dist/index.iife.js"></script>
<script>
navigator.modelContext.registerTool({ /* ... */ });
</script>Or with React: pnpm add @mcp-b/react-webmcp
import { useWebMCP } from '@mcp-b/react-webmcp';
function TodoApp({ todos, addTodo }) {
useWebMCP({
name: 'add_todo',
description: 'Add a new todo item',
schema: { title: z.string().describe('Todo title') },
execute: async ({ title }) => {
addTodo(title);
return { success: true };
},
});
return <ul>{todos.map(t => <li key={t.id}>{t.title}</li>)}</ul>;
}Three ways for AI agents to discover and call your tools:
┌─────────────────────────────────────────────────────────┐
│ Your website │
│ navigator.modelContext.registerTool({ ... }) │
└────────┬────────────────────┬───────────────────┬───────┘
│ │ │
┌────▼─────┐ ┌────────▼────────┐ ┌─────▼──────┐
│ MCP-B │ │ Chrome Native │ │ Local │
│Extension │ │ (experimental) │ │ Relay │
└────┬─────┘ └────────┬────────┘ └─────┬──────┘
│ │ │
▼ ▼ ▼
AI agent in Browser's Claude Desktop
browser built-in agent Cursor, VS Code
MCP-b Extension — Install from docs.mcp-b.ai/extension. Discovers tools on any page.
Chrome Native — Enable at chrome://flags → Experimental Web Platform features, or:
google-chrome --enable-experimental-web-platform-featuresSee Chromium flags reference for macOS / Windows / Linux commands.
Local Relay — Add to your MCP client config (Claude Desktop, Cursor, etc.):
{
"mcpServers": {
"webmcp-local-relay": {
"command": "npx",
"args": ["-y", "@mcp-b/webmcp-local-relay@latest"]
}
}
}Any website running @mcp-b/global becomes callable from your desktop AI agent. See the relay README for details.
| I want to… | Package |
|---|---|
| Add tools to my site (simplest) | @mcp-b/global |
| Just the polyfill, no MCP bridge | @mcp-b/webmcp-polyfill |
| Register tools from React | @mcp-b/react-webmcp |
| Forward tools to local AI agents | @mcp-b/webmcp-local-relay |
| Build a Chrome extension with tools | @mcp-b/extension-tools |
| Control Chrome from an AI agent | @mcp-b/chrome-devtools-mcp |
| Just the TypeScript types | @mcp-b/webmcp-types |
# Full runtime: polyfill + MCP bridge (most users start here)
pnpm add @mcp-b/global
# Strict WebMCP core polyfill only (no MCP extensions)
pnpm add @mcp-b/webmcp-polyfill
# TypeScript definitions (dev dependency)
pnpm add -D @mcp-b/webmcp-types
# React hooks for full runtime
pnpm add @mcp-b/react-webmcp zod
# React hooks for strict WebMCP core only
pnpm add usewebmcp zod
# Transport layer (custom integrations)
pnpm add @mcp-b/transports
# Chrome Extension API tools
pnpm add @mcp-b/extension-tools
# DOM extraction for AI
pnpm add @mcp-b/smart-dom-reader| Package | Version | Description |
|---|---|---|
| @mcp-b/webmcp-polyfill | navigator.modelContext polyfill — strict spec-aligned surface |
|
| @mcp-b/webmcp-types | TypeScript definitions for the WebMCP core API | |
| @mcp-b/global | Full runtime — polyfill + MCP bridge (prompts, resources, sampling) | |
| @mcp-b/webmcp-ts-sdk | Browser-adapted MCP TypeScript SDK with dynamic tool registration |
| Package | Version | Description |
|---|---|---|
| @mcp-b/transports | postMessage, iframe, and Chrome extension transports |
|
| @mcp-b/mcp-iframe | <mcp-iframe> web component — surfaces iframe tools to the parent page |
|
| @mcp-b/webmcp-local-relay | Localhost relay — forwards website tools to Claude Desktop, Cursor, etc. |
| Package | Version | Description |
|---|---|---|
| @mcp-b/react-webmcp | React hooks for full runtime (register tools + consume MCP servers) | |
| usewebmcp | React hooks for strict WebMCP core only |
| Package | Version | Description |
|---|---|---|
| @mcp-b/extension-tools | Pre-built MCP tools for Chrome Extension APIs (tabs, bookmarks, history, …) | |
| @mcp-b/smart-dom-reader | Token-efficient DOM extraction for AI agents | |
| @mcp-b/chrome-devtools-mcp | MCP server for Chrome DevTools with WebMCP integration |
Deprecated packages
| Package | Status | Migration |
|---|---|---|
| Deprecated | Use @mcp-b/react-webmcp instead | |
| Removed | Use custom useWebMCP wrappers |
┌──────────────────────────────────────────────────────────┐
│ Your web app │
│ navigator.modelContext.registerTool({ ... }) │
├────────────── @mcp-b/global ─────────────────────────────┤
│ MCP bridge: prompts, resources, sampling, elicitation │
├────────────── @mcp-b/webmcp-ts-sdk ──────────────────────┤
│ BrowserMcpServer — wraps native/polyfill context │
├────────────── @mcp-b/webmcp-polyfill ────────────────────┤
│ Strict WebMCP core (registerTool, provideContext, …) │
├──────────────────────────────────────────────────────────┤
│ Native browser API (when available) │
└──────────────────────────────────────────────────────────┘
▲ ▲
│ postMessage / extension │ WebSocket
▼ ▼
AI agent in browser Local AI agent
(extension, tab) (Claude Desktop, Cursor)
webmcp-types (canonical type definitions)
├── webmcp-polyfill (canonical runtime polyfill)
├── webmcp-ts-sdk (TypeScript SDK adapter)
├── transports (browser transports)
│ ├── mcp-iframe (iframe custom element)
│ └── global (full MCP-B runtime)
│ └── react-webmcp (React hooks for MCP-B)
└── usewebmcp (React hooks for strict core)
Standalone packages: extension-tools, smart-dom-reader, chrome-devtools-mcp, webmcp-local-relay.
git clone https://github.com/WebMCP-org/npm-packages.git
cd npm-packages
pnpm install
pnpm build| Command | What it does |
|---|---|
pnpm build |
Build all packages |
pnpm typecheck |
Type-check all packages |
pnpm check |
Lint + format (Biome) |
pnpm test:unit |
Unit tests |
pnpm test:e2e |
E2E tests (Playwright) |
pnpm test |
All tests |
pnpm --filter <pkg> build |
Build a single package |
pnpm --filter <pkg> test |
Test a single package |
pnpm changeset |
Create a changeset for versioning |
Prerequisites: Node.js >= 22.12 (see .nvmrc), pnpm >= 10
| Document | Purpose |
|---|---|
| CONTRIBUTING.md | How to contribute: setup, PR process, commit format |
| CLAUDE.md | Quick reference for AI agents working in this repo |
| Package Philosophy | Package boundaries and layering model |
| Testing Philosophy | Test layers, mocking policy, coverage expectations |
| E2E Testing | Playwright setup, test apps, debugging |
| @mcp-b/global guide | Advanced usage for the full runtime |
| @mcp-b/react-webmcp guide | Advanced React patterns |
| WebMCP Alignment Matrix | Spec vs native vs polyfill parity tracking |
| AI Contribution Manifesto | Safety rules and code quality bar |
| Relevant Links | Curated external best practices for contributors |
Contributions welcome — see CONTRIBUTING.md for guidelines.