AI agents use add_cookie to create or update resources in Selenium — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Selenium environment.
Adding cookies is a reversible Write operation that modifies browser state. While it could facilitate security attacks (e.g., session hijacking if combined with domain-level access), the operation itself is not destructive and can be undone by deleting the cookie.
From the tool's definition Tool name 'add_cookie' and description 'Add a cookie' indicates the tool creates or modifies cookie data in the browser. Cookies are persistent client-side data that persist across browser sessions.
Attacks that exploit this kind of access
Add a cookie. Browser must be on a page from the cookie's domain. It is categorised as a Write tool in the Selenium MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Selenium MCP server in PolicyLayer and add a rule for add_cookie: 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.
add_cookie 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 add_cookie 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 add_cookie. 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.
add_cookie 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 →