run_js_ephemeral · Dynamic MCP: Risk & Policy

WHAT IT DOES

What run_js_ephemeral does on Dynamic

AI agents invoke run_js_ephemeral to trigger actions in Dynamic. 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 run_js_ephemeral needs a policy

This tool allows execution of arbitrary Node.js code in a sandbox environment. Even though sandboxing provides some containment, the capability to run arbitrary code gives an AI agent the ability to execute external operations with effects dependent on the provided arguments. The lack of persistence does not reduce risk—ephemeral execution of arbitrary code is still Execute category.

From the tool's definition Tool description explicitly states 'Execute one-off Node.js code in the configured execution sandbox' and operates within sandboxes (Docker or Node). The tool name includes 'run_js_ephemeral' which clearly indicates arbitrary code execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_js_ephemeral Rate-limited

run_js_ephemeral 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": {
    "run_js_ephemeral": {
      "limits": [
        {
          "counter": "run_js_ephemeral_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 Dynamic, so you can run agents against it safely.

FAQ

Questions about run_js_ephemeral

What does the run_js_ephemeral tool do? +

Execute one-off Node.js code in the configured execution sandbox (Docker preferred, Node fallback) without persisting a tool. It is categorised as a Execute tool in the Dynamic MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_js_ephemeral? +

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

What risk level is run_js_ephemeral? +

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

Can I rate-limit run_js_ephemeral? +

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

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

run_js_ephemeral is provided by the Dynamic MCP server (mcpland/dynamic-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.