reset_odoo_shell
AI agents call reset_odoo_shell to permanently remove resources in MCP Odoo Shell — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although the description is empty and confidence is reduced accordingly, the tool name 'reset_odoo_shell' in a database/ORM context (Odoo) strongly suggests an irreversible operation. Reset operations on database shells can wipe data, state, or configurations that cannot be undone. This is more severe than Execute (which is reversible via side effects) and qualifies as Destructive.
From the tool's definition Tool name 'reset_odoo_shell' combined with context that this is an Odoo shell bridge allowing 'execution of Python code within an Odoo database context'.
Attacks that exploit this kind of access
reset_odoo_shell. It is categorised as a Destructive tool in the MCP Odoo Shell MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Odoo Shell MCP server in PolicyLayer and add a rule for reset_odoo_shell: 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 Odoo Shell. Nothing to install.
reset_odoo_shell 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 reset_odoo_shell 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 reset_odoo_shell. 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.
reset_odoo_shell is provided by the MCP Odoo Shell MCP server (seletz/mcp-odoo-shell). 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 →