Low Risk

cmux_browser_get

Get data from the browser page (url, title, text, html, value, attribute, element count).

How to control cmux_browser_get ↓

What cmux_browser_get does on Cmux Agent

AI agents call cmux_browser_get 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.

Low Risk

Why cmux_browser_get needs a policy

This tool retrieves information from a browser page (URL, title, text content, HTML, element values, attributes, counts) without modifying, executing code, or performing destructive actions. It is purely informational/query in nature, making it a Read category tool with low severity since data extraction from a page poses minimal risk compared to tools that execute code or manipulate state.

From the tool's definition Tool description states 'Get data from the browser page (url, title, text, html, value, attribute, element count)' - all retrieval operations with no side effects.

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

How to control cmux_browser_get

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_get:

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

cmux_browser_get 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 Cmux Agent — 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 cmux_browser_get

What does the cmux_browser_get tool do? +

Get data from the browser page (url, title, text, html, value, attribute, element count). It is categorised as a Read tool in the Cmux Agent MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on cmux_browser_get? +

Register the Cmux Agent MCP server in PolicyLayer and add a rule for cmux_browser_get: 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.

What risk level is cmux_browser_get? +

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

Can I rate-limit cmux_browser_get? +

Yes. Add a rate_limit block to the cmux_browser_get 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 cmux_browser_get completely? +

Set action: deny in the PolicyLayer policy for cmux_browser_get. 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 cmux_browser_get? +

cmux_browser_get 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.

Enforce policy on every Cmux Agent tool call.

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.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.