Return browser cookies for the current domain.
AI agents call list_cookies to retrieve information from SeleniumMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns existing cookie data without creating, modifying, or deleting anything. It is a passive information retrieval operation that does not alter system state. While cookies may contain sensitive data (session tokens, auth credentials), the risk is informational rather than operational, making it a Read classification with low severity.
From the tool's definition Tool name 'list_cookies' and description 'Return browser cookies for the current domain' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Return browser cookies for the current domain. It is categorised as a Read tool in the SeleniumMCP MCP Server, which means it retrieves data without modifying state.
Register the Selenium MCP server in PolicyLayer and add a rule for list_cookies: 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 SeleniumMCP. Nothing to install.
list_cookies 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 list_cookies 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 list_cookies. 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.
list_cookies is provided by the Selenium MCP server (lokii0911/seleniummcp). 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 →