Inspect a URL with the headless browser. Actions: headers (security headers), dom (forms+links+scripts), network (request log), forms, cookies, screenshot.
AI agents call browser_inspect to retrieve information from Pentest Ai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads and retrieves information from a URL using a headless browser — capturing headers, DOM elements, network requests, cookies, and screenshots. These are all passive observation/read actions with no modification of data.
From the tool's definition Inspect a URL with the headless browser... headers, dom, forms+links+scripts, network (request log), forms, cookies, screenshot
Documented attack patterns abuse exactly the kind of access browser_inspect gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pentest Ai, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_inspect:
{
"version": "1",
"default": "deny",
"tools": {
"browser_inspect": {}
}
}browser_inspect 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.
Inspect a URL with the headless browser. Actions: headers (security headers), dom (forms+links+scripts), network (request log), forms, cookies, screenshot. It is categorised as a Read tool in the Pentest Ai MCP Server, which means it retrieves data without modifying state.
Register the Pentest Ai MCP server in PolicyLayer and add a rule for browser_inspect: 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 Pentest Ai. Nothing to install.
browser_inspect 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_inspect 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_inspect. 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_inspect is provided by the Pentest Ai MCP server (0xsteph/pentest-ai). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 51 Pentest Ai tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
51 Pentest Ai tools catalogued and risk-classified — across an index of 42,500+ MCP servers.