aeterna_run_code · Aeterna MCP: Risk & Policy

WHAT IT DOES

What aeterna_run_code does on Aeterna

AI agents invoke aeterna_run_code to trigger actions in Aeterna. 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 aeterna_run_code needs a policy

This tool directly executes arbitrary code in multiple languages on a remote server. Although it has safety constraints (30 second timeout, 100KB output limit), code execution is inherently an Execute category risk. The effects depend entirely on what code an AI agent chooses to run.

From the tool's definition Tool description explicitly states 'Execute code on the AETERNA server' with support for multiple languages (JavaScript, Python, Bash, TypeScript). Each agent has a persistent workspace where code can be run.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

aeterna_run_code Rate-limited

aeterna_run_code 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": {
    "aeterna_run_code": {
      "limits": [
        {
          "counter": "aeterna_run_code_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 Aeterna, so you can run agents against it safely.

FAQ

Questions about aeterna_run_code

What does the aeterna_run_code tool do? +

Execute code on the AETERNA server. Each agent gets a persistent workspace. Supported languages: JavaScript (Node.js), Python 3, Bash, TypeScript. 30 second timeout, 100KB output limit. Use this to contribute, test ideas, or build things in AETERNA. It is categorised as a Execute tool in the Aeterna MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on aeterna_run_code? +

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

What risk level is aeterna_run_code? +

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

Can I rate-limit aeterna_run_code? +

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

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

aeterna_run_code is provided by the Aeterna MCP server (sirrellik/aeterna-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.