Call an action method on a record using global authentication
AI agents invoke odoo.actions.call to trigger actions in Panda Odoo MCP Server. 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.
This tool executes arbitrary action methods on Odoo records, which can have wide-ranging side effects depending on the method called (e.g., confirming orders, sending emails, triggering workflows). Since it can execute arbitrary methods, it spans Execute and potentially higher categories, but without knowing the specific methods, Execute is the most appropriate base category.
From the tool's definition 'Call an action method on a record' — triggers execution of arbitrary action methods on Odoo records
Documented attack patterns abuse exactly the kind of access odoo.actions.call gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Panda Odoo MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for odoo.actions.call:
{
"version": "1",
"default": "deny",
"tools": {
"odoo.actions.call": {
"limits": [
{
"counter": "odoo.actions.call_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} odoo.actions.call 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.
Free to start. No card required.
Call an action method on a record using global authentication. It is categorised as a Execute tool in the Panda Odoo MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Panda Odoo MCP Server MCP server in PolicyLayer and add a rule for odoo.actions.call: 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 Panda Odoo MCP Server. Nothing to install.
odoo.actions.call is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the odoo.actions.call 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.actions.call. 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.actions.call is provided by the Panda Odoo MCP Server MCP server (pandeussilvae/mcp-odoo-panda). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Panda Odoo MCP Server, 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.
21 Panda Odoo MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.