AI agents call cmux_browser_screenshot to retrieve information from Cmux Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves visual information (a screenshot) from the current browser state. It has no side effects, does not modify data, execute code, or perform destructive actions. It is purely observational, making it a Read operation. The severity is low because screenshots alone pose minimal risk—the blast radius from misuse is limited to information disclosure of what is currently visible in the browser.
From the tool's definition Tool name is 'cmux_browser_screenshot' and description states 'Take a screenshot of the browser page.' Screenshots capture visual state without modifying data or executing code.
Documented attack patterns abuse exactly the kind of access cmux_browser_screenshot gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cmux Agent, and nothing reaches the server without passing your rules. This is the rule we recommend for cmux_browser_screenshot:
{
"version": "1",
"default": "deny",
"tools": {
"cmux_browser_screenshot": {}
}
}cmux_browser_screenshot 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.
Take a screenshot of the browser page. It is categorised as a Read tool in the Cmux Agent MCP Server, which means it retrieves data without modifying state.
Register the Cmux Agent MCP server in PolicyLayer and add a rule for cmux_browser_screenshot: 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 Cmux Agent. Nothing to install.
cmux_browser_screenshot 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 cmux_browser_screenshot 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 cmux_browser_screenshot. 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.
cmux_browser_screenshot is provided by the Cmux Agent MCP server (multiagentcognition/cmux-agent-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Cmux Agent, 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.
63 Cmux Agent tools catalogued and risk-classified — across an index of 43,000+ MCP servers.