AI agents call browser_get_console_logs to retrieve information from Byob without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool passively retrieves browser console logs and uncaught JavaScript errors. It has no side effects, does not modify state, and does not execute code or trigger external operations.
From the tool's definition 'Read recent console.log/info/warn/error/debug entries' — the tool retrieves logging output and JavaScript errors without modifying or executing operations
Attacks that exploit this kind of access
Read recent console.log/info/warn/error/debug entries plus uncaught JavaScript. It is categorised as a Read tool in the Byob MCP Server, which means it retrieves data without modifying state.
Register the Byob MCP server in PolicyLayer and add a rule for browser_get_console_logs: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Byob. Nothing to install.
browser_get_console_logs is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the browser_get_console_logs rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for browser_get_console_logs. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
browser_get_console_logs is provided by the Byob MCP server (wxtsky/byob). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.