apply_change · Safe Migrations MCP: Risk & Policy

WHAT IT DOES

What apply_change does on Safe Migrations

AI agents use apply_change to create or update resources in Safe Migrations — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Safe Migrations environment.

WHY IT NEEDS A POLICY

Why apply_change needs a policy

While apply_change affects production systems and has significant blast radius if misused by an AI agent (could corrupt database or configuration), the gatekeeper design with mandatory proposal + simulation + confirmation token prevents arbitrary execution. This is a controlled Write operation, not an Execute tool (which would run arbitrary code).

From the tool's definition Tool description states 'Apply a proposal' which creates or modifies data. The gatekeeper architecture (requiring proposals, dry-runs, and confirmation tokens) indicates reversible changes rather than irreversible deletion, distinguishing this from…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

apply_change Rate-limited

apply_change stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "apply_change": {
      "limits": [
        {
          "counter": "apply_change_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Safe Migrations, so you can run agents against it safely.

FAQ

Questions about apply_change

What does the apply_change tool do? +

Apply a proposal. Requires the one-time confirmation token from simulate_impact. It is categorised as a Write tool in the Safe Migrations MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on apply_change? +

Register the Safe Migrations MCP server in PolicyLayer and add a rule for apply_change: 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 Safe Migrations. Nothing to install.

What risk level is apply_change? +

apply_change is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit apply_change? +

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

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

apply_change is provided by the Safe Migrations MCP server (possibly6/safe-migrations-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.