calc.eval · TOOL4LM MCP: Risk & Policy

WHAT IT DOES

What calc.eval does on TOOL4LM

AI agents invoke calc.eval to trigger actions in TOOL4LM. 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 calc.eval needs a policy

Evaluating arbitrary math expressions constitutes code/expression execution. While described as having no external calls and limited to math, expression evaluators can sometimes be abused (e.g., via injected logic or resource exhaustion). Severity is medium because the blast radius is limited compared to shell execution, but arbitrary expression evaluation still carries risk.

From the tool's definition "Evaluate math expression" — the tool executes/evaluates an expression, running computation based on user-supplied input

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

calc.eval Rate-limited

calc.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": {
    "calc.eval": {
      "limits": [
        {
          "counter": "calc.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 TOOL4LM, so you can run agents against it safely.

FAQ

Questions about calc.eval

What does the calc.eval tool do? +

Evaluate math expression (no external calls). It is categorised as a Execute tool in the TOOL4LM MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on calc.eval? +

Register the TOOL4LM MCP server in PolicyLayer and add a rule for calc.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 TOOL4LM. Nothing to install.

What risk level is calc.eval? +

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

Can I rate-limit calc.eval? +

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

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

calc.eval is provided by the TOOL4LM MCP server (khanhs-234/tool4lm). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

calc.eval is one line of TOOL4LM's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →