AI agents call browser_network_requests to retrieve information from Playwright without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name suggests reading/listing network request data (a common Playwright feature for inspecting intercepted HTTP traffic). No description is available to confirm side effects. Given the Read-leaning name and context of sibling tools (many are browser interaction/state tools), Read is most likely. Medium severity because network request data can contain sensitive information like auth tokens or cookies.
From the tool's definition Tool name is 'browser_network_requests'; description is empty. Based on name alone, this tool likely retrieves/lists network requests captured by the browser.
Documented attack patterns abuse exactly the kind of access browser_network_requests 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_network_requests:
{
"version": "1",
"default": "deny",
"tools": {
"browser_network_requests": {}
}
}browser_network_requests is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
browser_network_requests. It is categorised as a Read tool in the Playwright MCP Server, which means it retrieves data without modifying state.
Register the Playwright MCP server in PolicyLayer and add a rule for browser_network_requests: 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_network_requests 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_network_requests 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_network_requests. 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_network_requests 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.