AI agents call browser_get_cookies to retrieve information from MCProxy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data (cookies) from a browser session without modifying or deleting them, placing it in the Read category. The severity is medium rather than low because cookies frequently contain sensitive authentication credentials, session tokens, or personally identifiable information that could be misused if an agent exfiltrates them.
From the tool's definition Tool name 'browser_get_cookies' and description 'Get cookies from the browser session' indicate data retrieval with no modification. However, cookies often contain sensitive authentication tokens and session identifiers.
Attacks that exploit this kind of access
Get cookies from the browser session. Useful for saving authentication state. It is categorised as a Read tool in the MCProxy MCP Server, which means it retrieves data without modifying state.
Register the MCProxy MCP server in PolicyLayer and add a rule for browser_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 MCProxy. Nothing to install.
browser_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 browser_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 browser_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.
browser_get_cookies is provided by the MCProxy MCP server (saladtechnologies/mcproxy). 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 →