AI agents use manage_manufacturing 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.
The tool likely covers the full lifecycle of manufacturing operations (create, update, confirm, produce), making Write the most probable category. However, since the description is extremely sparse, confidence is reduced. Given it interacts with production orders in an ERP, misuse could disrupt critical business operations, warranting high severity.
From the tool's definition 'Manufacturing and production management' - the tool name 'manage_manufacturing' and description imply creating, updating, and controlling manufacturing orders and production workflows in an ERP system.
Attacks that exploit this kind of access
Manufacturing and production 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_manufacturing: 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_manufacturing 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_manufacturing 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_manufacturing. 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_manufacturing 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 →