AI agents call search_count to retrieve information from Odoo MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves statistical information (record count) based on search criteria. It has no side effects, creates no changes to data, executes no external operations, and poses minimal risk. It is a pure read operation consistent with the Read category definition.
From the tool's definition Tool name 'search_count' and description 'Count records matching search criteria' indicate a read-only operation that queries and returns aggregate data without modifying or executing any operations.
Documented attack patterns abuse exactly the kind of access search_count gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Odoo MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_count:
{
"version": "1",
"default": "deny",
"tools": {
"search_count": {}
}
}search_count is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Count records matching search criteria. It is categorised as a Read tool in the Odoo MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Odoo MCP Server MCP server in PolicyLayer and add a rule for search_count: 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 MCP Server. Nothing to install.
search_count 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 search_count 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 search_count. 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.
search_count is provided by the Odoo MCP Server MCP server (vzeman/odoo-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from 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.
12 Odoo MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.