Run an allowlisted long-running read operation in the background
AI agents use submit_async_task to create or update resources in Odoo MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Odoo MCP Server environment.
An AI agent can call submit_async_task faster than any human can review — one bad instruction and it creates or modifies resources in Odoo MCP Server by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Run an allowlisted long-running read operation in the background. It is categorised as a Write tool in the Odoo MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Odoo MCP Server MCP server in PolicyLayer and add a rule for submit_async_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 Odoo MCP Server. Nothing to install.
submit_async_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 submit_async_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 submit_async_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.
submit_async_task is provided by the Odoo MCP Server MCP server (pypi:odoo-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.