generate_model · MCP Software Engineer MCP: Risk & Policy

WHAT IT DOES

What generate_model does on MCP Software Engineer

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

WHY IT NEEDS A POLICY

Why generate_model needs a policy

This tool creates and adds new database models/entities, which is a reversible Write operation that modifies the database schema. It has high severity because misconfigured models could break application logic, create security vulnerabilities (e.g., missing authentication fields), or cause cascading issues across the system.

From the tool's definition Tool name 'generate_model' and description 'Generate database model/entity' indicate the tool creates new database schemas, models, or entities, which modifies the database structure.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

generate_model Rate-limited

generate_model 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": {
    "generate_model": {
      "limits": [
        {
          "counter": "generate_model_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 MCP Software Engineer, so you can run agents against it safely.

FAQ

Questions about generate_model

What does the generate_model tool do? +

Generate database model/entity. It is categorised as a Write tool in the MCP Software Engineer MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on generate_model? +

Register the MCP Software Engineer MCP server in PolicyLayer and add a rule for generate_model: 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 generate_model? +

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

Can I rate-limit generate_model? +

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

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

generate_model 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.

// THE FULL RECORD

generate_model is one line of MCP Software Engineer's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →