odoo_invoke_action · Odooclaw MCP: Risk & Policy

WHAT IT DOES

What odoo_invoke_action does on Odooclaw

AI agents invoke odoo_invoke_action to trigger actions in Odooclaw. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why odoo_invoke_action needs a policy

The term 'invoke_action' is a direct instruction to execute a named action in Odoo. Actions in ERPs can perform almost any operation—creating records, changing states, triggering automations, sending notifications, or executing custom code. Without a description, the blast radius cannot be constrained.

From the tool's definition Tool name 'odoo_invoke_action' indicates execution of arbitrary Odoo actions; in ERP context, actions trigger business logic, workflows, and state changes whose effects depend entirely on which action is invoked.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

odoo_invoke_action Rate-limited

odoo_invoke_action stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "odoo_invoke_action": {
      "limits": [
        {
          "counter": "odoo_invoke_action_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Odooclaw, so you can run agents against it safely.

FAQ

Questions about odoo_invoke_action

What does the odoo_invoke_action tool do? +

odoo_invoke_action. It is categorised as a Execute tool in the Odooclaw MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on odoo_invoke_action? +

Register the Odooclaw MCP server in PolicyLayer and add a rule for odoo_invoke_action: 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.

What risk level is odoo_invoke_action? +

odoo_invoke_action is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit odoo_invoke_action? +

Yes. Add a rate_limit block to the odoo_invoke_action 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.

How do I block odoo_invoke_action completely? +

Set action: deny in the PolicyLayer policy for odoo_invoke_action. 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.

What MCP server provides odoo_invoke_action? +

odoo_invoke_action 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.