evaluate_simple_smalltalk · Pharo Nc MCP: Risk & Policy

WHAT IT DOES

What evaluate_simple_smalltalk does on Pharo Nc

AI agents invoke evaluate_simple_smalltalk 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_simple_smalltalk needs a policy

Based on the server context (evaluating Pharo Smalltalk expressions via NeoConsole) and the tool name pattern matching sibling tools like 'evaluate_simple' and 'evaluate_code', this tool almost certainly executes Smalltalk code. Code execution tools can have broad effects depending on the expressions evaluated. Description is empty, reducing confidence slightly.

From the tool's definition Tool name contains 'evaluate' and 'smalltalk', and sibling tools include 'evaluate_code', 'evaluate_smalltalk_with_neo_console' which run Pharo Smalltalk expressions. Description is empty.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

evaluate_simple_smalltalk Rate-limited

evaluate_simple_smalltalk 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_simple_smalltalk": {
      "limits": [
        {
          "counter": "evaluate_simple_smalltalk_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_simple_smalltalk

What does the evaluate_simple_smalltalk tool do? +

evaluate_simple_smalltalk. 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_simple_smalltalk? +

Register the Pharo Nc MCP server in PolicyLayer and add a rule for evaluate_simple_smalltalk: 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_simple_smalltalk? +

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

Can I rate-limit evaluate_simple_smalltalk? +

Yes. Add a rate_limit block to the evaluate_simple_smalltalk 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_simple_smalltalk completely? +

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

evaluate_simple_smalltalk 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.