Read-only aggregate fanned out across instances with combined grand totals
AI agents call aggregate_across_instances 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 and aggregates data across multiple Odoo instances without creating, modifying, or deleting any information. The 'read-only' designation combined with aggregation and totaling operations are characteristic of data query and reporting functions, which pose minimal risk when misused by an AI agent.
From the tool's definition Tool description explicitly states 'Read-only aggregate' and 'fanned out across instances with combined grand totals' indicating data retrieval and aggregation without modification.
Attacks that exploit this kind of access
Read-only aggregate fanned out across instances with combined grand totals. 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 aggregate_across_instances: 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.
aggregate_across_instances 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 aggregate_across_instances 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 aggregate_across_instances. 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.
aggregate_across_instances is provided by the Odoo MCP Server MCP server (pypi:odoo-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.