WebMCP tool official reference-app
Risk level
low
10/100

WebMCP Page Agent

WebMCP Page Agent is an officially published WebMCP tool from GoogleChromeLabs. Anomity scores its risk at 10 out of 100 (low).

browser:control network:outbound

Analysis summary

WebMCP Page Agent is an officially published WebMCP tool from GoogleChromeLabs. Anomity scores its risk at 10 out of 100 (low).

A Gemini-powered controller that accepts natural language and drives whatever WebMCP tools the current page has registered. It is the reference demonstration of the full loop: a page publishes tools, a model reads them, the user types an intent, the model calls tools until the intent is satisfied.

This is the clearest illustration of why WebMCP belongs in a risk catalog. The agent's context includes page content, and page content is attacker-influenceable on any site that renders user input. The controller declares browser control and outbound network access. Anything that can get text in front of this agent is one injection away from calling the page's tools with arguments of its choosing — inside a session that is already authenticated.

Why this entry scored 10 out of 100

This profile starts at the catalog's neutral base of 50. Because the entry is officially published, trust adjusts the score by -40. The entry declares no high-risk capabilities on its own, so capabilities add nothing. It matches no dangerous capability combinations. The clamped result is 10, placing it in the low band.

See the full scoring formula →

Findings

  • Published by the vendor Trust offset
    Contribution to score: -40

Capabilities

Every capability the entry declares, with the security implication of each.

  • browser:control Browser control
    Drives a browser session. Combined with credential access can impersonate the user on web services.
  • network:outbound Outbound network
    Can make outbound network requests. Required for hosted model providers and remote APIs; also the path for data exfiltration if combined with read access.