crow_browser_evaluate

THE RISK

High Risk

Why crow_browser_evaluate needs a policy

This tool allows arbitrary JavaScript execution within a browser context. While the result is returned (not destructive by default), the ability to execute code means it can modify page state, steal data, trigger external calls, or perform actions dependent on the arguments passed. This is a classic Execute category risk, not Write (which is reversible) or Read (which has no side effects).

From the tool's definition Tool name and description: 'Execute JavaScript in the page context and return the result' — this directly invokes code execution.

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

POLICY

How to control crow_browser_evaluate

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

policy.json

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

crow_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 Crow — 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 Crow tools

Financial crow_tax_prepare_from_documents One-step tax return preparation: creates a return from ALL confirmed documents uploaded th Financial crow_actual_create_transaction Create a new transaction. Amount in cents (negative = expense, positive = income). Financial crow_tax_set_capital_gains Add Schedule D capital gain/loss transactions. Destructive caddy_remove_site Remove a site block from the Caddyfile (matched by address) and reload Caddy. Destructive Destructive crow_bookstack_delete Delete a page or chapter from BookStack (irreversible) Destructive crow_campaign_delete Delete a campaign and all its posts. Requires confirmation. Destructive crow_crosspost_cancel Cancel a queued cross-post before its scheduled_at fires. Idempotent — cancelling an alrea Destructive crow_delete_context_section Delete a custom crow.md section. Protected sections cannot be deleted — only disabled. Sco

All 576 Crow 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 Crow → 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 crow_browser_evaluate

What does the crow_browser_evaluate tool do? +

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

How do I enforce a policy on crow_browser_evaluate? +

Register the Crow MCP server in PolicyLayer and add a rule for crow_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 Crow. Nothing to install.

What risk level is crow_browser_evaluate? +

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

Can I rate-limit crow_browser_evaluate? +

Yes. Add a rate_limit block to the crow_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 crow_browser_evaluate completely? +

Set action: deny in the PolicyLayer policy for crow_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 crow_browser_evaluate? +

crow_browser_evaluate is provided by the Crow MCP server (kh0pper/crow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Crow tool call.

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

CHECK YOUR STACK →