AI agents call get_console_logs to retrieve information from Selenium without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical console log data from a browser session without modifying, deleting, or executing any operations. It is a passive query operation that has no impact on the system or application state. The severity is low because console logs are typically non-sensitive debugging information, and retrieving them poses minimal risk even if accessed by an unauthorized agent.
From the tool's definition Tool name 'get_console_logs' and description 'Return all captured browser console log entries' indicate data retrieval with no side effects.
Attacks that exploit this kind of access
Return all captured browser console log entries. It is categorised as a Read tool in the Selenium MCP Server, which means it retrieves data without modifying state.
Register the Selenium MCP server in PolicyLayer and add a rule for 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 Selenium. Nothing to install.
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 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 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.
get_console_logs is provided by the Selenium MCP server (scv-consultants/selenium-mcp). 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 →