browser_evaluate

THE RISK

High Risk

Why browser_evaluate needs a policy

This tool allows execution of arbitrary JavaScript code in the active browser tab's context. While not destructive by default, it has the broadest capability to trigger side effects including modifying DOM, making network requests, accessing sensitive data, or triggering page interactions.

From the tool's definition Tool description states it can 'Run custom JavaScript inside the page context' with ability to return results. This enables arbitrary code execution within the browser environment.

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

POLICY

How to control browser_evaluate

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "browser_evaluate": {
      "limits": [
        {
          "counter": "browser_evaluate_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

browser_evaluate stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register YetiBrowser MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More YetiBrowser MCP tools

Execute browser_wait Wait for a specified time in seconds Execute browser_wait_for Wait until a selector appears (optionally visible) before continuing. Returns a fresh snap Execute browser_click Perform click on a web page Execute browser_drag Drag an element (like cards in a kanban board) onto a target element. Useful for sortable Execute browser_fill_form Fill multiple form fields in a single call. Supports inputs, textareas, selects, checkboxe Execute browser_handle_dialog Accept or dismiss the currently open alert/confirm/prompt dialog in the active tab. Execute browser_hover Hover over element on page Execute browser_press_key Press a key on the keyboard

All 17 YetiBrowser MCP tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in YetiBrowser MCP → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about browser_evaluate

What does the browser_evaluate tool do? +

Run custom JavaScript inside the page context and return the JSON-serializable result. It is categorised as a Execute tool in the YetiBrowser MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on browser_evaluate? +

Register the YetiBrowser MCP server in PolicyLayer and add a rule for browser_evaluate: 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 YetiBrowser MCP. Nothing to install.

What risk level is browser_evaluate? +

browser_evaluate is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit browser_evaluate? +

Yes. Add a rate_limit block to the browser_evaluate 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_evaluate completely? +

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

browser_evaluate is provided by the YetiBrowser MCP server (yetidevworks/yetibrowser-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every YetiBrowser MCP tool call.

Start from YetiBrowser MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →