[KongchangAI]
ConceptConsequential Hint

consequentialHint

A safety annotation in the WebMCP protocol that marks high-risk operations and requires the agent to obtain secondary user confirmation before each invocation, without offering an "always allow" option.

Timeline (last 90 days)

Oct 30

The Chrome team demonstrated three security annotations (hints) for WebMCP tool definitions: readOnlyHint, consequentialHint, and untrustedContentHint.

Unverified50%
Oct 30

The consequentialHint: true annotation requires the agent to double-confirm high-risk operations and does not offer an "always allow" option.

Unverified50%

All Facts (2)

Source Articles