execute_script · Selenium MCP: Risk & Policy

WHAT IT DOES

What execute_script does on SeleniumMCP

AI agents invoke execute_script to trigger actions in SeleniumMCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why execute_script needs a policy

This tool runs arbitrary JavaScript in the active browser page, which is a quintessential Execute action. JavaScript execution can trigger side effects such as DOM manipulation, API calls, data exfiltration, form submission, or malicious payloads.

From the tool's definition Tool name: 'execute_script'. Description: 'Execute JavaScript in the active page and return the JSON-serializable result.' The verb 'Execute' and capability to run arbitrary JavaScript code in a browser context are explicit.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_script Rate-limited

execute_script 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.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches SeleniumMCP, so you can run agents against it safely.

FAQ

Questions about execute_script

What does the execute_script tool do? +

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

How do I enforce a policy on execute_script? +

Register the Selenium MCP server in PolicyLayer and add a rule for execute_script: 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 SeleniumMCP. Nothing to install.

What risk level is execute_script? +

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

Can I rate-limit execute_script? +

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

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

execute_script is provided by the Selenium MCP server (lokii0911/seleniummcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.