AI agents call odoo_search to retrieve information from Odooclaw without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search operations are inherently read-based—they retrieve or query data without side effects. Despite the empty description lowering confidence slightly, the tool name is unambiguous. The low severity reflects minimal blast radius if misused: searching data poses no risk of data loss, modification, or financial harm. The confidence is 0.7 rather than higher due to the lack of descriptive detail.
From the tool's definition Tool name 'odoo_search' indicates a search operation, which is a read-only query function. The description is empty, but the name strongly suggests data retrieval without modification.
Attacks that exploit this kind of access
odoo_search. It is categorised as a Read tool in the Odooclaw MCP Server, which means it retrieves data without modifying state.
Register the Odooclaw MCP server in PolicyLayer and add a rule for odoo_search: 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.
odoo_search 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_search 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_search. 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_search 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.
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 →