AI agents call browser_annotate as a supporting operation in Playwright workflows.
The name suggests adding annotations (likely visual markups) to a browser view, which could be a Write or Read operation. However, with no description available and the name alone being ambiguous, confidence is very low. Annotations are typically non-destructive overlays.
From the tool's definition Tool name is 'browser_annotate'; description is empty and uninformative.
Documented attack patterns abuse exactly the kind of access browser_annotate gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Playwright, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_annotate:
{
"version": "1",
"default": "deny",
"tools": {
"browser_annotate": {
"limits": [
{
"counter": "browser_annotate_rate",
"window": "minute",
"max": 60,
"scope": "grant"
}
]
}
}
}browser_annotate gets a rate cap, and everything else on the server is denied unless you say otherwise.
Free to start. No card required.
browser_annotate. It is categorised as a Other tool in the Playwright MCP Server, which means it performs auxiliary operations.
Register the Playwright MCP server in PolicyLayer and add a rule for browser_annotate: 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 Playwright. Nothing to install.
browser_annotate is a Other tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the browser_annotate 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_annotate. 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_annotate is provided by the Playwright MCP server (@playwright/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Playwright, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
68 Playwright tools catalogued and risk-classified — across an index of 43,000+ MCP servers.