Critical Risk →

browser_cookies

Get or set cookies for the current browser session. Use 'get' to read all cookies (useful for debugging auth). Use 'set' to add cookies (useful for setting auth tokens). Use 'clear' to delete all cookies.

Risk signalsAccepts file system path (cookies[].path)

Part of the Screenshotsmcp server.

browser_cookies can permanently delete data in Screenshotsmcp, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE SCREENSHOTSMCP →

Free to start. No card required.

AI agents may call browser_cookies to permanently remove or destroy resources in Screenshotsmcp. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. PolicyLayer blocks destructive tools by default and requires explicit human approval before enabling them.

Without a policy, an AI agent could call browser_cookies in a loop, permanently destroying resources in Screenshotsmcp. There is no undo for destructive operations. PolicyLayer blocks this tool by default and only allows it when a human explicitly approves the action.

Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.

policy.json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "browser_cookies"
  ]
}

See the full Screenshotsmcp policy for all 56 tools.

Get this rule live on your own Screenshotsmcp server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY SCREENSHOTSMCP →

View all 56 tools →

These attack patterns abuse exactly the kind of access browser_cookies gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so browser_cookies only ever does what you allow.

SECURE SCREENSHOTSMCP →

Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.

What does the browser_cookies tool do? +

Get or set cookies for the current browser session. Use 'get' to read all cookies (useful for debugging auth). Use 'set' to add cookies (useful for setting auth tokens). Use 'clear' to delete all cookies.. It is categorised as a Destructive tool in the Screenshotsmcp MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on browser_cookies? +

Register the Screenshots MCP server in PolicyLayer and add a rule for browser_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 Screenshotsmcp. Nothing to install.

What risk level is browser_cookies? +

browser_cookies is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit browser_cookies? +

Yes. Add a rate_limit block to the browser_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.

How do I block browser_cookies completely? +

Set action: deny in the PolicyLayer policy for browser_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.

What MCP server provides browser_cookies? +

browser_cookies is provided by the Screenshots MCP server (relievedattention992-smithery/screenshotsmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Screenshotsmcp tool call.

Deterministic rules across all 56 Screenshotsmcp tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.