list_odoo_models
AI agents call list_odoo_models to retrieve information from MCP Odoo Shell without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'list' prefix and naming pattern strongly suggest a retrieval operation. In the Odoo ecosystem, listing models is a read-only introspection activity. The empty description lowers confidence slightly, but the tool name and its position alongside 'odoo_model_info' (clearly informational) and 'execute_odoo_code' (clearly executable) support classification as a Read operation with low severity.
From the tool's definition Tool name 'list_odoo_models' indicates listing/retrieval of model metadata. No description provided, but the name and context of sibling tools suggest this queries Odoo model information without modification.
Attacks that exploit this kind of access
list_odoo_models. It is categorised as a Read tool in the MCP Odoo Shell MCP Server, which means it retrieves data without modifying state.
Register the MCP Odoo Shell MCP server in PolicyLayer and add a rule for list_odoo_models: 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 MCP Odoo Shell. Nothing to install.
list_odoo_models is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_odoo_models 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 list_odoo_models. 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.
list_odoo_models is provided by the MCP Odoo Shell MCP server (seletz/mcp-odoo-shell). 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 →