AI agents use migrate-new to create or update resources in MCP Atlas — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Atlas environment.
This tool creates a new migration file, which is a reversible write operation. It does not execute migrations (which would be Execute), delete files (Destructive), or modify financial data. While creating migration files is generally safe, misuse by an AI agent could create numerous spurious migration files that clutter the codebase or confuse the version control history, warranting a medium severity rating.
From the tool's definition Tool name 'migrate-new' and description 'Create a new empty migration file in the migration directory' indicate file creation within the migration system.
Attacks that exploit this kind of access
Create a new empty migration file in the migration directory. It is categorised as a Write tool in the MCP Atlas MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Atlas MCP server in PolicyLayer and add a rule for migrate-new: 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 Atlas. Nothing to install.
migrate-new 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 migrate-new 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 migrate-new. 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.
migrate-new is provided by the MCP Atlas MCP server (mpreziuso/mcp-atlas). 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 →