AI agents use browser_set_cookies to create or update resources in MCProxy — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCProxy environment.
This tool writes cookie data into an active browser session, which can modify authentication state, session tokens, and other sensitive browser state. While reversible (cookies can be cleared), it can be misused to inject forged session credentials, hijack authenticated sessions, or bypass authentication controls — warranting a high severity rating.
From the tool's definition 'Set cookies in the browser session. Useful for restoring authentication state.'
Attacks that exploit this kind of access
Set cookies in the browser session. Useful for restoring authentication state. It is categorised as a Write tool in the MCProxy MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCProxy MCP server in PolicyLayer and add a rule for browser_set_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_set_cookies 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 browser_set_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_set_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_set_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 →