simulate_impact · Safe Migrations MCP: Risk & Policy

WHAT IT DOES

What simulate_impact does on Safe Migrations

AI agents invoke simulate_impact to trigger actions in Safe Migrations. 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 simulate_impact needs a policy

The tool runs database queries/operations as part of simulating a migration proposal. Although the transaction is rolled back (limiting side effects), the tool still executes potentially complex database logic that could have side effects during execution (e.g., consuming resources, triggering constraints, running user-defined functions).

From the tool's definition Tool description states it 'execute[s]' a proposal within 'a rolled-back transaction', indicating code execution (database operations) with transactional semantics.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

simulate_impact Rate-limited

simulate_impact 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": {
    "simulate_impact": {
      "limits": [
        {
          "counter": "simulate_impact_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 Safe Migrations, so you can run agents against it safely.

FAQ

Questions about simulate_impact

What does the simulate_impact tool do? +

Dry-run a proposal. DB proposals execute inside a rolled-back transaction. It is categorised as a Execute tool in the Safe Migrations MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on simulate_impact? +

Register the Safe Migrations MCP server in PolicyLayer and add a rule for simulate_impact: 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 simulate_impact? +

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

Can I rate-limit simulate_impact? +

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

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

simulate_impact 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.