eval_in_page · Pigeon MCP: Risk & Policy

WHAT IT DOES

What eval_in_page does on Pigeon

AI agents invoke eval_in_page to trigger actions in Pigeon. 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 eval_in_page needs a policy

This tool executes arbitrary JavaScript code inside a browser page. An AI agent could use it to exfiltrate data, manipulate the DOM, perform actions on behalf of the user, make network requests, or cause any number of unintended side effects. 'Arbitrary JavaScript' means there are essentially no restrictions on what can be run, making the blast radius critical.

From the tool's definition DANGER: runs arbitrary JavaScript in the page

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

eval_in_page Rate-limited

eval_in_page 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": {
    "eval_in_page": {
      "limits": [
        {
          "counter": "eval_in_page_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 Pigeon, so you can run agents against it safely.

FAQ

Questions about eval_in_page

What does the eval_in_page tool do? +

DANGER: runs arbitrary JavaScript in the page. It is categorised as a Execute tool in the Pigeon MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on eval_in_page? +

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

What risk level is eval_in_page? +

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

Can I rate-limit eval_in_page? +

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

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

eval_in_page is provided by the Pigeon MCP server (pepperonas/pigeon). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.