AI agents call get_cookies 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 only reads and retrieves cookie data from the browser session without modifying, deleting, or executing any operations. It is purely a query/fetch operation, fitting the Read category. Severity is low because cookie data, while potentially sensitive, is not destructive and does not trigger external operations or financial transactions.
From the tool's definition Tool name 'get_cookies' and description 'Get cookies. Returns all or a specific one by name' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get cookies. Returns all or a specific one by name. 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_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 Selenium. Nothing to install.
get_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 get_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 get_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.
get_cookies 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 →