AI agents use manage_security to create or update resources in Odoo-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Odoo-MCP environment.
While 'manage_security' could theoretically involve read-only audit queries, the verb 'manage' combined with 'security' in an ERP context typically implies creating, modifying, or updating security policies, roles, permissions, or audit configurations. This is reversible (Write category), not destructive, but has high severity due to the critical nature of security settings in an ERP system.
From the tool's definition Tool name 'manage_security' combined with description 'Security and audit management' in context of Odoo ERP system suggests modification of security settings, audit logs, or access controls.
Attacks that exploit this kind of access
Security and audit management. It is categorised as a Write tool in the Odoo-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Odoo- MCP server in PolicyLayer and add a rule for manage_security: 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_security is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the manage_security 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_security. 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_security 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 →