Get the DOM snapshot before and/or after a specific action. Use interactiveOnly=true to get only inputs/buttons/dropdowns (much smaller). Use depth to limit tree depth for orientation.
AI agents call e2e_get_dom_snapshot to retrieve information from Playwright Autopilot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
e2e_get_dom_snapshot retrieves and queries the current state of the DOM tree without creating, modifying, deleting, or executing side effects. It is a read-only debugging operation. The tool cannot change application state or trigger actions independently—it only observes and reports DOM structure. Low severity because misuse would only expose DOM information, not cause data loss or unauthorized operations.
From the tool's definition Tool performs DOM snapshot retrieval with no modification capabilities: 'Get the DOM snapshot before and/or after a specific action.' Parameters like 'interactiveOnly' and 'depth' filter/limit output but do not alter the DOM. This is purely introspective.
Documented attack patterns abuse exactly the kind of access e2e_get_dom_snapshot gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Playwright Autopilot, and nothing reaches the server without passing your rules. This is the rule we recommend for e2e_get_dom_snapshot:
{
"version": "1",
"default": "deny",
"tools": {
"e2e_get_dom_snapshot": {}
}
}e2e_get_dom_snapshot 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.
Get the DOM snapshot before and/or after a specific action. Use interactiveOnly=true to get only inputs/buttons/dropdowns (much smaller). Use depth to limit tree depth for orientation. It is categorised as a Read tool in the Playwright Autopilot MCP Server, which means it retrieves data without modifying state.
Register the Playwright Autopilot MCP server in PolicyLayer and add a rule for e2e_get_dom_snapshot: 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 Autopilot. Nothing to install.
e2e_get_dom_snapshot 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 e2e_get_dom_snapshot 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 e2e_get_dom_snapshot. 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.
e2e_get_dom_snapshot is provided by the Playwright Autopilot MCP server (kaizen-yutani/playwright-autopilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Playwright Autopilot, 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.
51 Playwright Autopilot tools catalogued and risk-classified — across an index of 43,000+ MCP servers.