Capture and retrieve console output from browser tabs
AI agents call chrome_console to retrieve information from Chrome MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The description says 'capture and retrieve' which sounds like a read operation. However, browser console access can potentially execute JavaScript depending on implementation. Given only the description, it appears to be reading/capturing existing console output rather than injecting code. Confidence is moderate because console tools sometimes have execution capabilities not mentioned in the description.
From the tool's definition Capture and retrieve console output from browser tabs
Attacks that exploit this kind of access
Capture and retrieve console output from browser tabs. It is categorised as a Read tool in the Chrome MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Chrome MCP Server MCP server in PolicyLayer and add a rule for chrome_console: 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 Chrome MCP Server. Nothing to install.
chrome_console 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 chrome_console 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 chrome_console. 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.
chrome_console is provided by the Chrome MCP Server MCP server (mnisred/mcp-chrome). 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 →