Skip to content
Skills Library
AI & agents · Automation

webmcp-setup

/webmcp-setup

Set up a WebMCP project — enable Chrome flags, install MCP-B polyfill, scaffold tool registration, and configure development environment. Use when starting a new WebMCP-enabled website from scratch.

Licence
MIT
Last repository change
14.09.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
2
Deprecation

No signals detected. Repository changed on 14.09.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Set up a WebMCP project — enable Chrome flags, install MCP-B polyfill, scaffold tool registration, and configure development environment. Use when starting a new WebMCP-enabled website from scratch.

Original author description

Set up a WebMCP project — enable Chrome flags, install MCP-B polyfill, scaffold tool registration, and configure development environment. Use when starting a new WebMCP-enabled website from scratch.

How it works

  1. Before writing code
  2. Conceptual Architecture
Original SKILL.md headings · 89 lines, 587 words
SKILL.md preview
---
name: webmcp-setup
description: Set up a WebMCP project — enable Chrome flags, install MCP-B polyfill, scaffold tool registration, and configure development environment. Use when starting a new WebMCP-enabled website from scratch.
allowed-tools: Read, Write, Edit, Bash, Grep, Glob, WebSearch, WebFetch
---

# WebMCP Project Setup

## Before writing code

**Fetch live docs**:
1. Fetch `https://webmachinelearning.github.io/webmcp/` — the **W3C Community Group draft report**, which is the normative spec for `navigator.modelContext`. Start here, not with vendor docs.
2. Fetch `https://developer.chrome.com/docs/ai/webmcp` for Chrome's implementation notes and API overview.
3. Web-search `site:github.com mcp-b polyfill README` for polyfill installation and quickstart.
4. Web-search `webmcp chrome flag enable` for current browser flag names and version requirements — these change per milestone.
5. Web-search `site:chromestatus.com webmcp` for feature status and shipping milestones.

**Standards status**: WebMCP is a **W3C Community Group Draft Report** hosted by the Web Machine Learning CG — it is *not* a W3C Standard and is *not* on the W3C Standards Track. Chrome is the reference implementation; other engines have participated in discussion without shipping. Plan for the API surface to move, keep the polyfill path viable, and re-check browser support rather than assuming it broadened.

## Conceptual Architecture

### What Setup Involves

WebMCP project setup prepares a website to expose tools to AI agents:
1. **Enable browser support** — Chrome 146+ Canary with the `WebMCP for Testing` flag, or install the MCP-B polyfill
2. **Install polyfill (if needed)** — `mcp-b` packages for vanilla JS or React
3. **Scaffold tool registration** — create the entry point where tools are registered via `navigator.modelContext.registerTool()`
4. **Configure development environment** — set up testing with AI agents

### Project Structure (Vanilla JS)

```
my-webmcp-site/
├── src/
│   ├── webmcp/
│   │   ├── tools.js              # Tool definitions and registration
│   │   ├── schemas.js            # JSON Schemas for tool inputs
│   │   └── interactions.js       # User interaction handlers
│   ├── index.html                # Page with optional declarative form attributes
│   └── app.js                    # Main application entry
├── package.json
└── tests/
    └── webmcp.test.js
```

### Project Structure (React + MCP-B)

```
my-webmcp-react-app/
├── src/
│   ├── webmcp/
│   │   ├── tools.ts              # Tool definitions
│   │   ├── schemas.ts            # JSON Schemas
│   │   ├── McpProvider.tsx        # MCP-B React provider/hooks wrapper
│   │   └── interactions.ts       # User interaction logic
│   ├── App.tsx
│   └── index.tsx
├── package.json
├── tsconfig.json
└── tests/
    └── webmcp.test.tsx
```

### Setup Decision Checklist

- **Browser target** — Native Chrome 146+ (flag-gated) or polyfill for broader support?
- **Framework** — Vanilla JS, React, Vue, or server-rendered HTML?
- **API approach** — Imperative (JS `registerTool`), Declarative (HTML attributes), or both?
- **Tool scope** — Which user journeys will be exposed as tools?
- **Authentication** — What user role is required before registering sensitive tools?
- **Testing strategy** — Which AI agents to test with (Gemini, Claude, etc.)?

### Chrome Flag Setup

To enable native WebMCP in Chrome Canary:
1. Install Chrome 146+ Canary
2. Navigate to `chrome://flags`
3. Search for the WebMCP flag (name may change — search for it live)
4. Enable the flag and restart Chrome

### MCP-B Polyfill Setup

For browsers without native WebMCP, the MCP-B polyfill provides the same API surface. Fetch the README for exact installation commands, as packages and APIs may have changed.

### Best Practices

- Start with one or two simple read-only tools before adding transactional ones
- Use the polyfill for development even if targeting native Chrome — it works everywhere
- Register tools after the page has loaded and the user is authenticated
- Group related tools logically (all cart tools together, all search tools together)
- Test tool discovery with at least one AI agent before going to production

Fetch the latest Chrome blog post and MCP-B README for exact commands, package names, and API patterns before scaffolding.

Versions

The database has no other skills named webmcp-setup.

Database snapshot: 13.11.2026 · package version 6df662e9c82f (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100webmcp-polyfill
    Set up and use the MCP-B polyfill — vanilla JS and React packages that implement navigator.modelContext for browsers without native WebMCP. Use when developing for browsers that don't yet support WebMCP natively.
  • 100crestapps-core-webmcp
    Skill for WebMCP in CrestApps.Core 2.0, the proposed W3C standard that lets a page give tools to browser AI agents through document.modelContext. Covers CrestApps.Core.AI.WebMcp with AddWebMcp and AddCoreAIWebMcp, MapWebMcpTools list and invoke endpoints, WebMcpOptions…
  • 100webmcp-testing
    Test WebMCP tools with AI agents — Chrome DevTools integration, agent testing workflows, tool discovery verification, and end-to-end commerce flow testing. Use when validating that tools work correctly with real AI agents.
  • 100webmcp-gen
    Build and validate experimental WebMCP tools for an existing web page. Use when an agent needs to expose a site's real workflows as page tools, create webmcp.init.js, define deterministic checks, or compare WebMCP with accessibility-tree automation.
  • 100webmcpx
    Add WebMCP tools to a website and check them. Use when a user wants AI agents to use their site, asks about WebMCP, navigator.modelContext or document.modelContext, registerTool, or wants to lint/validate WebMCP tool definitions.
  • 85webmcp
    In-page WebMCP tools (JavaScript functions or HTML tools) for front-ends. Use for Literate AI workflow tasks that expose MCP in the browser page. Inherits the MCP parent; not a second protocol.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.