AI agents call count_records to retrieve information from Odoo-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the database to return a count of matching records. It performs a read-only operation analogous to SQL COUNT(), retrieving metadata about data without creating, modifying, or deleting anything. Even in the context of an ERP system with sensitive data, counting records has minimal blast radius — an attacker gains only numeric information about data cardinality, not access to record contents.
From the tool's definition Tool name is 'count_records' and description states it 'Count records matching a domain' — a retrieval/aggregation operation with no mutation or side effects.
Attacks that exploit this kind of access
Count records matching a domain. It is categorised as a Read tool in the Odoo-MCP MCP Server, which means it retrieves data without modifying state.
Register the Odoo- MCP server in PolicyLayer and add a rule for count_records: 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. Nothing to install.
count_records 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 count_records 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 count_records. 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.
count_records is provided by the Odoo- MCP server (ridrisa/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 →