tla_evaluate · Tlaplus MCP: Risk & Policy

WHAT IT DOES

What tla_evaluate does on Tlaplus

AI agents invoke tla_evaluate to trigger actions in Tlaplus. 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 tla_evaluate needs a policy

This tool runs the TLC model checker to evaluate an arbitrary TLA+ expression, which constitutes executing external toolchain processes. While it creates a temporary spec, the execution of arbitrary expressions via TLC could have side effects depending on the expression content. It goes beyond simple reads as it actively invokes the TLC engine to compute results.

From the tool's definition 'Evaluate a constant TLA+ expression using TLC. Creates a temporary spec that prints the result of the expression.'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

tla_evaluate Rate-limited

tla_evaluate 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": {
    "tla_evaluate": {
      "limits": [
        {
          "counter": "tla_evaluate_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 Tlaplus, so you can run agents against it safely.

FAQ

Questions about tla_evaluate

What does the tla_evaluate tool do? +

Evaluate a constant TLA+ expression using TLC. Creates a temporary spec that prints the result of the expression. It is categorised as a Execute tool in the Tlaplus MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on tla_evaluate? +

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

What risk level is tla_evaluate? +

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

Can I rate-limit tla_evaluate? +

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

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

tla_evaluate is provided by the Tlaplus MCP server (richashworth/tlaplus-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.