ChromeWalk
io.github.chromewalk/chromewalk
Local browser automation for AI agents: real-browser fetch, capture, smoke tests, cross-engine QA.
Install surfaces
How ChromeWalk runs, per the official MCP registry entry.
- mcpb
https://github.com/chromewalk/app/releases/download/v15.0.0/ChromeWalk-Claude-Extension.mcpb
Governed execution
How KLA gates calls to ChromeWalk once it is connected.
A published policy defines which ChromeWalk actions an agent may take and under what conditions. Each call passes through a policy gate at the tool-call boundary. Permitted actions execute, with the policy basis recorded. Flagged actions execute and are sampled for scheduled human review. High-stakes actions pause and route to a named reviewer on the Decision Desk. The call, the policy decision, and any approval are sealed as an evidence record.
KLA also governs the agents and model providers you already run. See integrations.