run_migrations · MCP Software Engineer MCP: Risk & Policy

WHAT IT DOES

What run_migrations does on MCP Software Engineer

AI agents invoke run_migrations to trigger actions in MCP Software Engineer. 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 run_migrations needs a policy

Database migrations execute arbitrary SQL or programmatic changes to database schemas. While migrations are typically part of normal deployment workflows, they represent executable operations with significant side effects on production data.

From the tool's definition Tool performs 'Run database migrations' — a database operation that executes code (SQL scripts or migration scripts) against a database, potentially altering schema and data structures irreversibly.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_migrations Rate-limited

run_migrations 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": {
    "run_migrations": {
      "limits": [
        {
          "counter": "run_migrations_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 Software Engineer, so you can run agents against it safely.

FAQ

Questions about run_migrations

What does the run_migrations tool do? +

Run database migrations. It is categorised as a Execute tool in the MCP Software Engineer MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_migrations? +

Register the MCP Software Engineer MCP server in PolicyLayer and add a rule for run_migrations: 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 Software Engineer. Nothing to install.

What risk level is run_migrations? +

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

Can I rate-limit run_migrations? +

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

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

run_migrations is provided by the MCP Software Engineer MCP server (rajawatrajat/mcp-software-engineer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.