Restores a Firebird database from a backup
AI agents call restore-database to permanently remove resources in MCP Firebird — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
A database restore operation replaces the current live database with a backup, permanently and irreversibly overwriting all data added or modified after the backup point. This is among the most destructive operations possible on a database system, with a blast radius covering the entire database and all its data.
From the tool's definition 'Restores a Firebird database from a backup' — restoring a database overwrites the existing database with backup contents, irreversibly destroying any data written since the backup was taken.
Attacks that exploit this kind of access
Restores a Firebird database from a backup. It is categorised as a Destructive tool in the MCP Firebird MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Firebird MCP server in PolicyLayer and add a rule for restore-database: 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 Firebird. Nothing to install.
restore-database is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the restore-database 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 restore-database. 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.
restore-database is provided by the MCP Firebird MCP server (luancamara/mcpfirebird). 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 →