AI agents call get_companies to retrieve information from Odxproxy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query to retrieve company records. It does not create, modify, delete, or execute code. The blast radius is minimal since it only exposes data that an authorized Odoo user would already have access to. Severity is low because retrieving company information poses minimal risk, though exposure should still be controlled based on data sensitivity policies.
From the tool's definition Tool name is 'get_companies' and description states 'Retrieve company records from the Odoo' — retrieval with no modification or side effects.
Attacks that exploit this kind of access
Retrieve company records from the Odoo. It is categorised as a Read tool in the Odxproxy MCP Server, which means it retrieves data without modifying state.
Register the Odxproxy MCP server in PolicyLayer and add a rule for get_companies: 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 Odxproxy. Nothing to install.
get_companies 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 get_companies 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 get_companies. 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.
get_companies is provided by the Odxproxy MCP server (terrakernel/odxproxy-mcpserver). 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 →