3wbiz

Page Title
Live in Chrome 146

WebMCP Implementation Services

Declarative & Imperative API integration for agent-ready web applications.

Quick Spec Summary Standard: W3C Community Group Draft (Google + Microsoft, Chrome 146 early preview) APIs: Declarative (HTML form attributes) + Imperative (navigator.modelContext.registerTool()) Scope: Client-side, browser-native — no backend server required Auth: Inherits browser session (same-origin policy enforced) Security: HTTPS required, CSP-compatible, user confirmation for write operations

What We Implement

01
Low-Code

Declarative API

For standard HTML forms — the lowest-friction path to agent-readiness. We annotate existing forms with toolname and tooldescription attributes, write optimized tool descriptions that maximize agent discoverability, and validate the auto-generated schema against real agent call patterns.


<!-- Before -->
<form action='/contact' method='POST'>
  <input name='email' type='email' required>
  <button type='submit'>Submit</button>
</form>

<!-- After: WebMCP Declarative API -->
<form action='/contact' method='POST'
  toolname='bookConsultation'
  tooldescription='Book a free consultation.
    Accepts: name (text), email (email), serviceType
    (enum: seo|webdev|audit). Returns: confirmation.'>
  <input name='email' type='email' required>
  <button type='submit'>Submit</button>
</form>
02
High-Performance

Imperative API

For dynamic, data-driven tools that need custom execution logic. We design inputSchema objects following JSON Schema draft-07, implement execute() functions with proper async handling and error boundaries, and configure readOnly flags correctly for the browser confirmation model.


// WebMCP Imperative API Example
navigator.modelContext.registerTool({
  name: 'searchProducts',
  readOnly: true,
  description: 'Search product catalog...',
  inputSchema: {
    type: 'object',
    properties: {
      query: { type: 'string' },
      maxPrice: { type: 'number' },
      inStock: { type: 'boolean' }
    },
    required: ['query']
  },
  async execute({ query, maxPrice, inStock }) {
    const res = await fetch(`/api/search?q=${query}`);
    return { content: [{ type: 'text',
      text: await res.text() }] };
  }
});

Implementation Scope by Package

Starter

    Scope
  • Site audit + Declarative API on 3 forms
  • tool description copy
  • Inspector testing
  • handover doc
  • Timeline
  • 3–5 days
Most Popular

Growth

Scope
  • Imperative API + 5 tools
  • JSON Schema design
  • readOnly configuration
  • Shopify Storefront API integration
  • agent tracking (SubmitEvent.agentInvoked)
  • Timeline
  • 1–2 weeks

Enterprise

Scope
  • Full tool architecture audit
  • CSP compatibility review
  • rate limiting recommendations
  • security hardening
  • server-side validation review
  • monthly spec update monitoring
  • Timeline
  • 2–4 weeks

Technical Stack Compatibility

WebMCP is platform-agnostic — it runs client-side in the browser and does not depend on your backend stack. We have tested and documented implementation patterns for:

01
Shopify
Storefront API-backed tool execution, metafield-driven tool descriptions, theme-compatible injection
02
WordPress / WooCommerce
wp_enqueue_script() registration, WooCommerce REST API integration, Gutenberg-compatible
03
Next.js / React
useEffect() registration pattern, SSR-safe navigator.modelContext feature detection
04
Custom builds
Vanilla JS or any framework — the API is framework-agnostic
05
Wix / Squarespace / Duda
Declarative API via custom code injection (where platform permits custom JS)

Testing & Handover

Every implementation is tested using the Model Context Tool Inspector (Chrome DevTools extension) before handover. We document:

  • All registered tools with name, description, and schema
  • Test call log — parameters used, responses received
  • Maintenance guide — how to update tool descriptions and schemas when site features change
  • Spec monitoring notes — known upcoming changes in the W3C draft

Security Implementation

We follow W3C security guidance and implement defense-in-depth across all tool registrations:


readOnly flag discipline

All read/query tools set readOnly: true. All write/submit tools set readOnly: false to enforce browser confirmation.

Server-side validation

JSON Schema validates client-side for agent UX. Every tool endpoint validates and sanitizes server-side.

Rate limiting

Tool-backing endpoints get rate limits calibrated for agent traffic patterns (higher frequency than human form submissions).

Safe error responses

execute() functions use try/catch with user-safe messages — no stack traces or internal paths in tool responses.

Agent invocation logging

SubmitEvent.agentInvoked flag captured and logged for audit trail and analytics.

Least privilege exposure

Only public-safe capabilities are registered. Admin endpoints are never exposed as tools.

Free Assessment

Start With a
Technical Audit

We assess your current stack, form hygiene, HTTPS/CSP setup, and JS architecture, then deliver a detailed implementation plan with effort estimates per tool.

Request A Technical Audit

We respond within 24 hours.