AI agents invoke migrate_pg to trigger actions in Mementos. 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.
Applying schema migrations executes DDL statements against a live database (CREATE TABLE, ALTER TABLE, DROP TABLE, etc.), which can have irreversible side effects like dropping columns or tables. While it could be considered Destructive depending on the migration content, the primary action is executing database operations whose effects depend on the migration scripts.
From the tool's definition Apply PostgreSQL schema migrations to the configured RDS instance
Attacks that exploit this kind of access
Apply PostgreSQL schema migrations to the configured RDS instance. It is categorised as a Execute tool in the Mementos MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mementos MCP server in PolicyLayer and add a rule for migrate_pg: 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 Mementos. Nothing to install.
migrate_pg is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the migrate_pg 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_pg. 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_pg is provided by the Mementos MCP server (@hasna/mementos). 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 →