Diagnose ACL and record-rule visibility for an Odoo model
AI agents call diagnose_access 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 analyzes access control lists (ACLs) and record rules to determine visibility permissions—a diagnostic/informational operation with no side effects, data modification, or execution capability. It is purely informational and falls clearly under the Read category.
From the tool's definition Tool name 'diagnose_access' and description 'Diagnose ACL and record-rule visibility for an Odoo model' indicate querying and inspection of access control metadata without modification of data or execution of operations.
Attacks that exploit this kind of access
Diagnose ACL and record-rule visibility for an Odoo model. 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 diagnose_access: 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.
diagnose_access 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 diagnose_access 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 diagnose_access. 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.
diagnose_access 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.