evaluate

THE RISK

High Risk

Why evaluate needs a policy

This tool executes arbitrary JavaScript in a browser context via Chrome DevTools. An AI agent could use it to run any code, access DOM, exfiltrate data, manipulate pages, make network requests, or interact with browser storage. The blast radius is critical as there are virtually no constraints on what JavaScript can be executed.

From the tool's definition Tool name 'evaluate' and description 'Evaluates a JavaScript script'

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

POLICY

How to control evaluate

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

policy.json

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

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 Chrome DevTools — 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 Chrome DevTools tools

Destructive uninstall_extension Uninstalls a Chrome extension by its ID. Destructive close_heapsnapshot Closes a previously loaded memory heapsnapshot, freeing its memory. Destructive close_page Closes the page by its index. The last open page cannot be closed. Execute emulate Emulates various features on the selected page. Execute execute_3p_developer_tool Executes a tool exposed by the page. Execute execute_webmcp_tool Executes a WebMCP tool exposed by the page. Execute lighthouse_audit Get Lighthouse score and reports for accessibility, SEO, best practices, and agentic brows Execute navigate Loads a URL

All 50 Chrome DevTools 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

Govern code and CI agents → Branch allowlists, approval on merges, and rate caps on the build and pipeline tools agents trigger.
High-risk tools in Chrome DevTools → 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 →
PolicyLayer vs alternatives → How deterministic, per-call MCP policy compares with gateways, identity layers, and authorisation platforms.

FAQ

Questions about evaluate

What does the evaluate tool do? +

Evaluates a JavaScript script. 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 evaluate? +

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

What risk level is evaluate? +

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

Can I rate-limit evaluate? +

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

Set action: deny in the PolicyLayer policy for 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 evaluate? +

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

Enforce policy on every Chrome DevTools tool call.

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

CHECK YOUR STACK →