tla_parse · Tlaplus MCP: Risk & Policy

WHAT IT DOES

What tla_parse does on Tlaplus

AI agents invoke tla_parse 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_parse needs a policy

This tool runs the SANY parser/analyzer tool against TLA+ source code. While it is primarily a read/analysis operation with no persistent side effects, it executes an external toolchain process (SANY) on user-supplied content. It falls into Execute rather than Read because it invokes an external program whose behavior depends on the input.

From the tool's definition Parse and syntax-check a TLA+ module using SANY (Syntactic Analyzer)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

tla_parse Rate-limited

tla_parse 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_parse": {
      "limits": [
        {
          "counter": "tla_parse_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_parse

What does the tla_parse tool do? +

Parse and syntax-check a TLA+ module using SANY (Syntactic Analyzer). Returns parse errors and the list of modules parsed. 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_parse? +

Register the Tlaplus MCP server in PolicyLayer and add a rule for tla_parse: 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_parse? +

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

Can I rate-limit tla_parse? +

Yes. Add a rate_limit block to the tla_parse 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_parse completely? +

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

tla_parse 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.