Plan Odoo OWL frontend work with asset, registry, service, and test guardrails.
AI agents use plan_owl_feature to create or update resources in Odoo Dev MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Odoo Dev MCP environment.
This tool creates or organizes development plans and frontend structures (assets, registries, services, test guardrails) as part of Odoo module development. While it doesn't directly execute code or permanently delete data, it writes/generates development artifacts that modify the codebase state.
From the tool's definition Tool description states it is used to 'Plan Odoo OWL frontend work' and groups this server with tools like 'create_odoo_model', 'create_odoo_module', 'create_odoo_view', and 'create_owl_component', all of which generate or modify code artifacts.
Documented attack patterns abuse exactly the kind of access plan_owl_feature gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Odoo Dev MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for plan_owl_feature:
{
"version": "1",
"default": "deny",
"tools": {
"plan_owl_feature": {
"limits": [
{
"counter": "plan_owl_feature_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}plan_owl_feature stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Plan Odoo OWL frontend work with asset, registry, service, and test guardrails. It is categorised as a Write tool in the Odoo Dev MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Odoo Dev MCP server in PolicyLayer and add a rule for plan_owl_feature: 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 Dev MCP. Nothing to install.
plan_owl_feature 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 plan_owl_feature 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 plan_owl_feature. 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.
plan_owl_feature is provided by the Odoo Dev MCP server (mart337i/odoo-dev-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Odoo Dev MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
25 Odoo Dev MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.