AI agents call list_stock_alerts to retrieve information from Eyeot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns existing stock alert information. The verb 'list' is a classic read operation that retrieves data without side effects. Even in an ERP system context with ~600 business actions available, this specific tool performs monitoring/reporting functions only. The description suggests it displays alerts about inventory levels, which is purely informational.
From the tool's definition Tool name 'list_stock_alerts' and description 'Alertes stock bas / rupture' (low stock/shortage alerts) indicate retrieval of alert data with no modification or deletion capabilities.
Attacks that exploit this kind of access
Alertes stock bas / rupture. It is categorised as a Read tool in the Eyeot MCP Server, which means it retrieves data without modifying state.
Register the Eyeot MCP server in PolicyLayer and add a rule for list_stock_alerts: 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 Eyeot. Nothing to install.
list_stock_alerts 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 list_stock_alerts 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 list_stock_alerts. 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.
list_stock_alerts is provided by the Eyeot MCP server (https://erp.eyeot.fr/api/v1/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 →