Query the DOM of a Chrome/Electron page. Returns matching elements
AI agents call browser_dom to retrieve information from ScreenHand without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs DOM inspection/querying, which is a read-only information retrieval action. It queries the structure and content of a webpage without side effects. While DOM queries can inform subsequent actions (like clicks or form fills), the tool itself only retrieves and returns data. No modifications, code execution, deletions, or financial operations occur.
From the tool's definition Tool description states 'Query the DOM of a Chrome/Electron page. Returns matching elements' — a pure read operation that retrieves data without modifying or executing anything.
Documented attack patterns abuse exactly the kind of access browser_dom gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ScreenHand, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_dom:
{
"version": "1",
"default": "deny",
"tools": {
"browser_dom": {}
}
}browser_dom 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.
Query the DOM of a Chrome/Electron page. Returns matching elements. It is categorised as a Read tool in the ScreenHand MCP Server, which means it retrieves data without modifying state.
Register the ScreenHand MCP server in PolicyLayer and add a rule for browser_dom: 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 ScreenHand. Nothing to install.
browser_dom 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_dom 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_dom. 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_dom is provided by the ScreenHand MCP server (manushi4/screenhand). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ScreenHand, 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.
89 ScreenHand tools catalogued and risk-classified — across an index of 43,000+ MCP servers.