AI agents call odoo_read to retrieve information from Odoo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing records from Odoo by their identifier. It performs a query operation with no side effects, no data modification, and no destructive or financial impact. The low severity reflects minimal risk even if an AI agent misuses it, as read-only access cannot alter or delete data. The high confidence is based on the clear, explicit description that unambiguously indicates a read-only operation.
From the tool's definition Tool name is 'odoo_read' and description states 'Read Odoo records by id' — a retrieval operation with no modification or deletion capability.
Attacks that exploit this kind of access
Read Odoo records by id. It is categorised as a Read tool in the Odoo MCP Server, which means it retrieves data without modifying state.
Register the Odoo MCP server in PolicyLayer and add a rule for odoo_read: 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. Nothing to install.
odoo_read 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 odoo_read 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_read. 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_read is provided by the Odoo MCP server (plgonzalezrx8/odoo-mcp). 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 →