Diff two schemas (source = desired state, target = the DB to modify)
AI agents use generate_migration to create or update resources in Querybridge — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Querybridge environment.
This tool creates or modifies database schema reversibly (Write category). It does not delete data irreversibly (not Destructive), but enables schema changes that could have significant blast radius if misused by an agent (high severity).
From the tool's definition Tool diffs two schemas with source as 'desired state' and target as 'the DB to modify', indicating it generates instructions to alter a database schema.
Attacks that exploit this kind of access
Diff two schemas (source = desired state, target = the DB to modify). It is categorised as a Write tool in the Querybridge MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Querybridge MCP server in PolicyLayer and add a rule for generate_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 Querybridge. Nothing to install.
generate_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 generate_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 generate_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.
generate_migration is provided by the Querybridge MCP server (mahmoudhassanmustafa/querybridge-mcp). 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 →