check_drift · CodeFlow MCP Server MCP: Risk & Policy

WHAT IT DOES

What check_drift does on CodeFlow MCP Server

AI agents invoke check_drift to trigger actions in CodeFlow MCP Server. 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_drift needs a policy

The tool actively executes a drift detection process on the codebase, which involves running computational analysis rather than simply reading static data. It triggers an external operation whose effects depend on the current state of the codebase. No data is written, deleted, or financial transactions made, so Execute is the most appropriate category.

From the tool's definition 'Run drift detection on the current analyzed codebase' — the word 'Run' indicates active execution of an analysis process against the codebase

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

check_drift Rate-limited

check_drift 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_drift": {
      "limits": [
        {
          "counter": "check_drift_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 CodeFlow MCP Server, so you can run agents against it safely.

FAQ

Questions about check_drift

What does the check_drift tool do? +

Run drift detection on the current analyzed codebase. It is categorised as a Execute tool in the CodeFlow MCP Server 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_drift? +

Register the CodeFlow MCP Server MCP server in PolicyLayer and add a rule for check_drift: 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 CodeFlow MCP Server. Nothing to install.

What risk level is check_drift? +

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

Can I rate-limit check_drift? +

Yes. Add a rate_limit block to the check_drift 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_drift completely? +

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

check_drift is provided by the CodeFlow MCP Server MCP server (mrorigo/code-flow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.