webmcp-authentication
Implement WebMCP authentication patterns — browser session inheritance, cookie-based auth, role-gated tool registration, and conditional tool exposure. Use when managing which tools are available based on user authentication state.
Best use case
webmcp-authentication is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Implement WebMCP authentication patterns — browser session inheritance, cookie-based auth, role-gated tool registration, and conditional tool exposure. Use when managing which tools are available based on user authentication state.
Teams using webmcp-authentication should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/webmcp-authentication/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How webmcp-authentication Compares
| Feature / Agent | webmcp-authentication | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Implement WebMCP authentication patterns — browser session inheritance, cookie-based auth, role-gated tool registration, and conditional tool exposure. Use when managing which tools are available based on user authentication state.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# WebMCP Authentication
## Before writing code
**Fetch live docs**:
1. Fetch `https://webmachinelearning.github.io/webmcp/` for authentication-related sections of the spec
2. Web-search `webmcp authentication session cookies browser agent` for auth pattern guidance
3. Web-search `site:developer.chrome.com webmcp security authentication` for Chrome security model
4. Web-search `site:github.com mcp-b security authentication` for polyfill security guidance
## Conceptual Architecture
### How WebMCP Authentication Works
WebMCP's auth model is fundamentally different from backend API authentication:
1. **No separate agent login** — The agent inherits the user's browser session
2. **Cookies and headers** — Tools' fetch calls automatically include the user's cookies and auth headers
3. **Same-origin policy** — Tools operate within the page's origin, bound by standard browser security
4. **Session-based** — If the user is logged in, tools have the user's permissions; if not, tools have anonymous access
This means the agent **acts as the user**, not as a separate entity with its own credentials.
### Authentication Flow
```
User logs in to site (normal browser auth)
→ Page loads with authenticated session
→ JavaScript checks user auth state
→ If authenticated: register full tool set (search, cart, checkout, account)
→ If anonymous: register limited tool set (search, viewDetails only)
→ Agent discovers available tools based on current auth state
```
### Role-Gated Tool Registration
Register tools conditionally based on user permissions:
```js
// Always register read-only tools
registerPublicTools();
// Register transactional tools only for authenticated users
if (user.isAuthenticated) {
registerCartTools();
registerAccountTools();
}
// Register admin tools only for admin users
if (user.role === "admin") {
registerAdminTools();
}
```
### Auth State Changes
Handle login/logout during an agent session:
```js
// On login
authService.onLogin((user) => {
registerAuthenticatedTools(user);
});
// On logout
authService.onLogout(() => {
navigator.modelContext.clearContext();
registerPublicTools(); // Re-register only anonymous tools
});
```
### Session Expiration
Tools must handle session expiration gracefully:
```js
async execute(input) {
const res = await fetch("/api/cart", { credentials: "same-origin" });
if (res.status === 401) {
return {
status: "error",
code: "session_expired",
message: "Your session has expired. Please log in again."
};
}
return await res.json();
}
```
### Security Considerations
1. **Never expose auth tokens to the agent** — The agent doesn't need to see cookies or tokens; the browser handles them
2. **Server-side validation** — Always validate the session server-side; don't trust client-side auth checks alone
3. **CSRF protection** — Tools making POST requests should include CSRF tokens (the page already has them)
4. **Sensitive tools need confirmation** — Even authenticated users should confirm destructive actions via `requestUserInteraction`
5. **No credential storage** — Never register tools that accept passwords or credentials as parameters
### Multi-Factor Authentication
If an action requires MFA (e.g., changing payment method):
```js
async execute(input, client) {
// Check if action requires MFA
const mfaRequired = await fetch("/api/check-mfa-required");
if (mfaRequired) {
await client.requestUserInteraction((resolve) => {
// Site shows MFA challenge (OTP input, biometric prompt, etc.)
showMfaChallenge(resolve);
});
}
// Proceed with the action
// ...
}
```
### Best Practices
- Check auth state before registering tools, not during tool execution
- Clear all tools on logout to prevent stale tool exposure
- Return clear, structured error responses for auth failures
- Never pass sensitive user data (email, address, card) as tool input parameters — fetch it server-side
- Log tool invocations with user identity for audit trails
- Handle token refresh transparently within tool callbacks
Fetch the specification for any authentication-specific APIs, secure context requirements, and browser permission model details before implementing.Related Skills
webmcp-user-interaction
Implement human-in-the-loop flows with requestUserInteraction() — confirmation dialogs, approval workflows, and user prompts during tool execution. Use when building tools that require user consent before performing actions.
webmcp-tool-schemas
Design JSON Schemas for WebMCP tool inputs and outputs — proper types, constraints, nested objects, and agent-friendly documentation. Use when defining or refining tool schemas for agent consumption.
webmcp-tool-annotations
Implement WebMCP tool annotations — readOnlyHint, destructiveHint, idempotentHint safety hints that inform browser permission prompts and agent behavior. Use when marking tools with appropriate safety metadata.
webmcp-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.
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.
webmcp-security
Implement WebMCP security best practices — permission model, data minimization, honest descriptions, input validation, fingerprinting prevention, and fraud mitigation. Use when auditing or hardening WebMCP tool implementations.
webmcp-register-tool
Implement the WebMCP Imperative API — register tools via navigator.modelContext.registerTool() with proper schemas, execute callbacks, and lifecycle management. Use when building dynamic tool registration in JavaScript.
webmcp-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.
webmcp-mcp-bridge
Integrate WebMCP client-side tools with backend MCP servers and UCP endpoints — bridge browser-based agent interactions with server-to-server protocols. Use when connecting front-end WebMCP to existing backend API infrastructure.
webmcp-context-provider
Implement the WebMCP provideContext API — bulk tool registration, contextual metadata, page state sharing, and dynamic context updates. Use when providing rich context and multiple tools to agents simultaneously.
webmcp-commerce-tools
Implement commerce-specific WebMCP tools — product search, cart management, checkout, returns, subscriptions, and support. Use when building agentic shopping experiences on e-commerce websites.
a2a-authentication
Implement A2A authentication — API keys, Bearer tokens, OAuth 2.0, OpenID Connect, and mutual TLS. Use when securing agent-to-agent communication and configuring Agent Card security schemes.