Pre-action authority receipts for DevTools MCP actions

[rpelevin]

Hi maintainers/users - I am testing an authority-before-action receipt pattern for MCP-backed browser and DevTools actions used by coding agents.

The narrow question is: before an agent uses a privileged browser/devtools surface, can the workflow prove what exact action is authorized, what target it applies to, and whether it should proceed, revise, stop, or route to human review?

I put a credential-free dry-run benchmark here:

https://github.com/neurarelay/relay-action-card

For this repo, the closest starting path is:

npm run benchmark:agent-authority -- --dry-run --json --source=github_discussion --campaign=agent_authority_week --surface=chrome_devtools_mcp_browser_authority

This is not a Chrome DevTools MCP approval, endorsement, integration, partnership, listing, pass, or fail claim. It is a proposed boundary pattern for authority-before-action around MCP-accessible browser/devtools capabilities.

Question for maintainers/users here: is a pre-action authority receipt useful for DevTools MCP workflows, or would the better insertion point be somewhere else in the execution lifecycle?