Backup and recovery operations
AI agents call manage_backup_recovery to permanently remove resources in Odoo-MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Backup and recovery operations on an ERP system are highly privileged. Recovery (restore) operations are inherently destructive as they overwrite the current database state with a previous snapshot, which is irreversible. Even backup operations expose the entire database. Given the Odoo ERP context with employee records, financials, and holidays, misuse could cause catastrophic data loss or corruption.
From the tool's definition 'Backup and recovery operations' — recovery operations can overwrite existing data irreversibly; backup operations interact with full database state
Attacks that exploit this kind of access
Backup and recovery operations. It is categorised as a Destructive tool in the Odoo-MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Odoo- MCP server in PolicyLayer and add a rule for manage_backup_recovery: 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 Odoo-MCP. Nothing to install.
manage_backup_recovery 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 manage_backup_recovery 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 manage_backup_recovery. 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.
manage_backup_recovery is provided by the Odoo- MCP server (ridrisa/odoo-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 →