Cambia el user agent a uno aleatorio.
AI agents use randomize_user_agent to create or update resources in MCP Selenium WebDriver — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Selenium WebDriver environment.
This tool modifies the browser session configuration by changing the user agent string. It's a reversible configuration change (Write), not destructive. The blast radius is low as it only affects how the browser identifies itself to web servers, which could impact fingerprinting/detection evasion but doesn't directly harm data or systems.
From the tool's definition Cambia el user agent a uno aleatorio (Changes the user agent to a random one)
Attacks that exploit this kind of access
Cambia el user agent a uno aleatorio. It is categorised as a Write tool in the MCP Selenium WebDriver MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Selenium WebDriver MCP server in PolicyLayer and add a rule for randomize_user_agent: 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 MCP Selenium WebDriver. Nothing to install.
randomize_user_agent is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the randomize_user_agent 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 randomize_user_agent. 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.
randomize_user_agent is provided by the MCP Selenium WebDriver MCP server (nixon-suarez/mcp-selenium-webdriver). 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 →