eval · Nextjs Agent MCP: Risk & Policy

WHAT IT DOES

What eval does on Nextjs Agent

AI agents invoke eval to trigger actions in Nextjs Agent. 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 needs a policy

This tool allows an AI agent to execute any JavaScript code in the active tab without constraints. This is a classic Execute pattern because JavaScript can trigger any browser capability (network requests, DOM manipulation, navigation, storage access, etc.).

From the tool's definition "Execute arbitrary JavaScript in the tab" — the tool explicitly permits running arbitrary code within the browser context.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

eval Rate-limited

eval 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": {
      "limits": [
        {
          "counter": "eval_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 Nextjs Agent, so you can run agents against it safely.

FAQ

Questions about eval

What does the eval tool do? +

Execute arbitrary JavaScript in the tab and return the serialized result. The snippet may. It is categorised as a Execute tool in the Nextjs Agent 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? +

Register the Nextjs Agent MCP server in PolicyLayer and add a rule for eval: 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 Nextjs Agent. Nothing to install.

What risk level is eval? +

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

Can I rate-limit eval? +

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

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

eval is provided by the Nextjs Agent MCP server (zohaib3249/nextjs-agent-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.