WebMCP

Browser-native API proposal for exposing structured webpage tools to AI agents.

Who launched it and why

  • WebMCP is being developed through the Web Machine Learning Community Group as a browser API proposal.
  • Chrome announced an early preview program in 2026 to help websites expose reliable structured actions for agents.
  • It was created to reduce brittle DOM-actuation automation by letting sites define intentional tool interfaces.

What it is

  • An API surface (e.g., navigator.modelContext) for webpages to register tool definitions and execution handlers.
  • Supports declarative and imperative interaction patterns depending on complexity and app state.
  • Designed to align conceptually with MCP primitives while remaining web-platform-native and browser-mediated.

Who it is for

  • Web application teams that want agents to perform deterministic actions in complex product UIs.
  • Platform and browser teams working on safe/permissioned agent execution models.
  • AI product teams shipping in-browser assistants and agent workflows.

How to implement it (practical path)

  1. Identify high-value user journeys where agent execution beats brittle UI scripting (checkout, support tickets, filtering, booking).
  2. Design tool contracts with strict input schemas and deterministic execution outputs.
  3. Implement feature detection, fallback UX, and permission-aware controls for agent requests.
  4. Track tool usage, failures, and user overrides to improve tool coverage and reliability over time.

CMS and platform implementation playbook

WordPress

  • Expose front-end JavaScript tool adapters on key templates (support, forms, product pages) while calling hardened backend APIs.
  • Keep write actions server-authorized and role-bound; never trust client-only tool calls for privileged operations.
  • Use plugin architecture to centralize tool registration and per-page capability toggles.

Shopify

  • Map WebMCP tool interactions to storefront tasks (product filtering, cart updates) and secure backend app proxies.
  • Use Shopify functions and app scopes for strict permissioning of transactional actions.
  • Treat checkout-critical actions as server-confirmed workflows, not purely client-side tool side effects.

Webflow

  • Add structured tool hooks to critical interactive components and route writes through secure serverless endpoints.
  • Ensure UI state always reflects tool-driven changes (WebMCP proposal explicitly calls out UI synchronization importance).
  • Keep content retrieval paths CMS-backed and expose only minimum write scope needed.

Headless (Next.js/React/Vue)

  • Wrap tool registration in a dedicated agent-integration layer with schema validation and telemetry.
  • Use SSR/edge APIs for privileged execution while browser tools orchestrate intent capture and UX updates.
  • Design for progressive enhancement because WebMCP browser support remains early-stage.

CMS-specific implementation guides

Detailed runbooks for deploying WebMCP on major CMS platforms.

Implementing WebMCP on WordPress

Plugin architecture, REST mappings, auth controls, and rollout checklist.

Open guide →

Implementing WebMCP on Shopify

GraphQL integration strategy, scope controls, and transactional safety patterns.

Open guide →

Implementing WebMCP on Webflow

Data API integration, publishing workflows, and rate-limit safe orchestration.

Open guide →

Implementing WebMCP on Drupal

JSON:API and module architecture with role-safe content and capability exposure.

Open guide →

Implementing WebMCP on HubSpot CMS

HubL templates, HubDB/CMS APIs, and serverless enforcement for secure actions.

Open guide →

Implementing WebMCP on Contentful

CMA/CDA orchestration, environment promotion, and optimistic-lock-safe mutations.

Open guide →

Official documentation

Third-party references