execute_in_page_tool · Chrome Devtools MCP: Risk & Policy

WHAT IT DOES

What execute_in_page_tool does on Chrome Devtools

AI agents invoke execute_in_page_tool to trigger actions in Chrome Devtools. 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_in_page_tool needs a policy

This tool triggers execution of arbitrary page-exposed functionality, which can perform any action the page permits (navigation, DOM manipulation, API calls, data exfiltration, etc.). The effects are determined entirely by the page's exposed tools and user input, making it an Execute category risk.

From the tool's definition Tool name 'execute_in_page_tool' and description 'Executes a tool exposed by the page' indicate code/script execution within a browser context.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_in_page_tool Rate-limited

execute_in_page_tool 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_in_page_tool": {
      "limits": [
        {
          "counter": "execute_in_page_tool_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 Chrome Devtools, so you can run agents against it safely.

FAQ

Questions about execute_in_page_tool

What does the execute_in_page_tool tool do? +

Executes a tool exposed by the page. It is categorised as a Execute tool in the Chrome Devtools 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_in_page_tool? +

Register the Chrome Devtools MCP server in PolicyLayer and add a rule for execute_in_page_tool: 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 Chrome Devtools. Nothing to install.

What risk level is execute_in_page_tool? +

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

Can I rate-limit execute_in_page_tool? +

Yes. Add a rate_limit block to the execute_in_page_tool 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_in_page_tool completely? +

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

execute_in_page_tool is provided by the Chrome Devtools MCP server (shivamprasad99/chrome-devtools-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.