evaluate_code · Pharo Nc MCP: Risk & Policy

WHAT IT DOES

What evaluate_code does on Pharo Nc

AI agents invoke evaluate_code to trigger actions in Pharo Nc. 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 evaluate_code needs a policy

This tool executes arbitrary Pharo Smalltalk code in a live environment. Arbitrary code execution means an AI agent could run any expression, including file system operations, network calls, process spawning, or destructive system modifications. The blast radius is critical since Smalltalk has full access to the host system and the Pharo image.

From the tool's definition "Evaluate a Pharo Smalltalk expression using NeoConsole"

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

evaluate_code Rate-limited

evaluate_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": {
    "evaluate_code": {
      "limits": [
        {
          "counter": "evaluate_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 Pharo Nc, so you can run agents against it safely.

FAQ

Questions about evaluate_code

What does the evaluate_code tool do? +

Evaluate a Pharo Smalltalk expression using NeoConsole. It is categorised as a Execute tool in the Pharo Nc MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on evaluate_code? +

Register the Pharo Nc MCP server in PolicyLayer and add a rule for evaluate_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 Pharo Nc. Nothing to install.

What risk level is evaluate_code? +

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

Can I rate-limit evaluate_code? +

Yes. Add a rate_limit block to the evaluate_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 evaluate_code completely? +

Set action: deny in the PolicyLayer policy for evaluate_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 evaluate_code? +

evaluate_code is provided by the Pharo Nc MCP server (mumez/pharo-nc-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.