AI agents call browser_console_get to retrieve information from Browser without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
browser_console_get retrieves previously captured console output. It performs a read-only operation that queries logging data already recorded by the browser console. There is no creation, modification, deletion, code execution, or external state change triggered by calling this tool.
From the tool's definition Tool name and description indicate retrieval of console logs: 'Get all captured console logs'. This is a query operation with no side effects on the browser state or external systems.
Attacks that exploit this kind of access
Get all captured console logs since browser_console_start was called (see browser_docs). It is categorised as a Read tool in the Browser MCP Server, which means it retrieves data without modifying state.
Register the Browser MCP server in PolicyLayer and add a rule for browser_console_get: 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 Browser. Nothing to install.
browser_console_get 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_console_get 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_console_get. 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_console_get is provided by the Browser MCP server (ricardodeazambuja/browser-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →