从备份文件恢复数据库
AI agents call restore_database to permanently remove resources in PySqlitMCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Restoring a database is an irreversible destructive operation: it replaces the live database with backup contents, permanently losing any changes made after the backup point. This qualifies as Destructive with critical severity because an AI agent misusing this tool could wipe out an entire database's current state.
From the tool's definition restore_database — '从备份文件恢复数据库' (restore database from backup file). Restoring a database overwrites the current database state entirely and irreversibly, destroying all data written since the backup was taken.
Attacks that exploit this kind of access
从备份文件恢复数据库. It is categorised as a Destructive tool in the PySqlitMCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the PySqlit 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 PySqlitMCP. 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 PySqlit MCP server (python51888/pysqlitmcp). 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 →