check_code_enforced · MCP Pyrefly MCP: Risk & Policy

WHAT IT DOES

What check_code_enforced does on MCP Pyrefly

AI agents invoke check_code_enforced to trigger actions in MCP Pyrefly. 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 check_code_enforced needs a policy

This tool does more than passively read or query; it enforces a behavioral constraint by blocking progress until fixes are made. This constitutes an external operation with side effects on the agent's execution flow and session state.

From the tool's definition 'Check code with enforcement - blocks progress until fixes are made' - triggers external enforcement behavior that controls agent flow

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

check_code_enforced Rate-limited

check_code_enforced 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": {
    "check_code_enforced": {
      "limits": [
        {
          "counter": "check_code_enforced_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 MCP Pyrefly, so you can run agents against it safely.

FAQ

Questions about check_code_enforced

What does the check_code_enforced tool do? +

Check code with enforcement - blocks progress until fixes are made. It is categorised as a Execute tool in the MCP Pyrefly MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on check_code_enforced? +

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

What risk level is check_code_enforced? +

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

Can I rate-limit check_code_enforced? +

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

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

check_code_enforced is provided by the MCP Pyrefly MCP server (kimasplund/mcp-pyrefly). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.