WebMCPGoogle
· Roadmap · Context Plane · Learning path
Formal document · Technical direction

Architecture & boundaries

A practical guide to exposing website capabilities to AI agents without confusing discoverability with authority. This document describes design principles and candidate patterns; it is not a statement that every capability is implemented or that WebMCP is a ratified part of the MCP specification.

A person working with connected digital tools
Status: guidance; implementation evidence required

1. Purpose and scope

WebMCP concerns the browser/page boundary: how a website can describe and expose structured actions to compatible agent experiences. MCP is the broader protocol for connecting AI applications to tools and context. The two are related but not interchangeable. This site is an independent Tech 4 Humanity project, not an official Chrome or MCP project.

2. Design principles

Discoverability is not permission.

A tool description helps a client understand an operation. It does not grant the user’s authority, bypass site policy, or make page content trustworthy.

Least privilege by default.

Expose the smallest useful operation, validate all inputs server-side or at the trusted execution boundary, scope identity and permissions, and deny unknown capabilities.

Human control for consequential changes.

Writes, publication, external communications, purchases, account changes and destructive operations need explicit approval bound to the exact action and payload.

Evidence over demonstration.

A screenshot, static page, API-presence check or unit test alone does not prove end-to-end execution. Record target, action, before/after state, receipt, denial path and recovery result.

3. Integration patterns

The preferred first step is one low-risk end-to-end use case with a defined fallback, not implementing every adapter in parallel.

4. Safety and trust model

5. Proposed context-plane relationship

A shared context engine may normalise permitted inputs, preserve provenance, classify freshness and sensitivity, link duplicates and contradictions, create task-specific context packs, validate the pack, and emit receipts. Candidate interfaces such as context.capture, context.inspect and context.pack.validate remain proposals until the owners agree schemas, permissions and lifecycle policy. They are not existing endpoints merely because they are documented.

6. Verification requirements

7. Sources