AI agents use odoo_create_task to create or update resources in Odooclaw — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Odooclaw environment.
This tool creates new task records in Odoo ERP, which is a Write operation as it adds data to the system reversibly. It does not delete (Destructive), execute arbitrary code (Execute), move money (Financial), or merely read (Read). The severity is medium because creating arbitrary tasks could clutter the system or cause workflow disruptions, but the impact is limited in scope and reversible.
From the tool's definition Tool name is 'odoo_create_task' which clearly indicates creation of a new task record. The 'create' verb combined with the Odoo ERP context indicates reversible data modification.
Attacks that exploit this kind of access
odoo_create_task. It is categorised as a Write tool in the Odooclaw MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Odooclaw MCP server in PolicyLayer and add a rule for odoo_create_task: 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 Odooclaw. Nothing to install.
odoo_create_task 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 odoo_create_task 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_create_task. 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_create_task is provided by the Odooclaw MCP server (nicolasramos/odooclaw-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 →