Create database migration
AI agents use create_migration 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.
Database migrations are reversible modifications to database schemas (adding tables, columns, indexes, etc.). This is a Write operation because it creates new artifacts that change database state, but is not Destructive since migrations are typically reversible and can be rolled back.
From the tool's definition Tool name 'create_migration' and description 'Create database migration' indicate the tool creates new database migration files/artifacts that modify database schema or structure.
Attacks that exploit this kind of access
Create database migration. 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.
Register the MCP Software Engineer MCP server in PolicyLayer and add a rule for create_migration: 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.
create_migration is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_migration 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.
Set action: deny in the PolicyLayer policy for create_migration. 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.
create_migration 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →