Delete Odoo records after safety checks.
AI agents call odoo_unlink to permanently remove resources in Odoo — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The 'unlink' operation in Odoo is the standard method for permanently deleting records. This is a destructive action that cannot be undone. Even with safety checks mentioned, the core functionality is irreversible deletion. In an ERP context where records represent business transactions, customers, inventory, and financial data, unauthorized or erroneous mass deletion could cause severe business disruption.
From the tool's definition Tool name 'odoo_unlink' and description 'Delete Odoo records after safety checks' explicitly indicate irreversible deletion of data records in an Odoo ERP system.
Attacks that exploit this kind of access
Delete Odoo records after safety checks. It is categorised as a Destructive tool in the Odoo 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 odoo_unlink: 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. Nothing to install.
odoo_unlink 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 odoo_unlink 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 odoo_unlink. 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.
odoo_unlink is provided by the Odoo MCP server (plgonzalezrx8/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 →