Retrieve all cookies from the browser context, optionally filtered by URLs.
AI agents call cookies_get to retrieve information from MCP Playwright Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves cookie data without side effects. However, severity is elevated to 'medium' rather than 'low' because cookies often contain sensitive authentication tokens, session IDs, and personal tracking data. An AI agent with access could exfiltrate credentials or private user information, though it cannot modify or delete cookies directly.
From the tool's definition Tool name is 'cookies_get' and description states 'Retrieve all cookies from the browser context' - both indicate read-only retrieval with no modification or deletion.
Attacks that exploit this kind of access
Retrieve all cookies from the browser context, optionally filtered by URLs. It is categorised as a Read tool in the MCP Playwright Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Playwright Server MCP server in PolicyLayer and add a rule for cookies_get: 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 Playwright Server. Nothing to install.
cookies_get 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 cookies_get 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 cookies_get. 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.
cookies_get is provided by the MCP Playwright Server MCP server (j0hanz/playwright-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 →