Low Risk

browser_screenshot_element

Screenshot a specific element by CSS selector.

How to control browser_screenshot_element ↓

What browser_screenshot_element does on Termux Browser Pilot

AI agents call browser_screenshot_element to retrieve information from Termux Browser Pilot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why browser_screenshot_element needs a policy

This tool only captures visual information from the browser without modifying any data, executing commands, or triggering side effects. The screenshot itself is read-only output. While browser automation tools can enable reconnaissance for attacks, this specific capability is limited to passive observation of rendered content, making it a Read operation with low severity.

From the tool's definition Tool takes a CSS selector and returns a screenshot of a DOM element. No modification of browser state, data, or external systems. Pure information retrieval.

Documented attack patterns abuse exactly the kind of access browser_screenshot_element gives an agent:

How to control browser_screenshot_element

PolicyLayer is an MCP gateway — it sits between your AI agents and Termux Browser Pilot, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_screenshot_element:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "browser_screenshot_element": {}
  }
}

browser_screenshot_element is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Termux Browser Pilot — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about browser_screenshot_element

What does the browser_screenshot_element tool do? +

Screenshot a specific element by CSS selector. It is categorised as a Read tool in the Termux Browser Pilot MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on browser_screenshot_element? +

Register the Termux Browser Pilot MCP server in PolicyLayer and add a rule for browser_screenshot_element: 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 Termux Browser Pilot. Nothing to install.

What risk level is browser_screenshot_element? +

browser_screenshot_element is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit browser_screenshot_element? +

Yes. Add a rate_limit block to the browser_screenshot_element 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.

How do I block browser_screenshot_element completely? +

Set action: deny in the PolicyLayer policy for browser_screenshot_element. 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.

What MCP server provides browser_screenshot_element? +

browser_screenshot_element is provided by the Termux Browser Pilot MCP server (salviz/termux-browser-pilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Termux Browser Pilot tool call.

Start from Termux Browser Pilot, 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.

148 Termux Browser Pilot tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.