list_products
AI agents call list_products to retrieve information from AdminAgent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool lists (retrieves) products, which is a read-only operation with no side effects. There is no evidence of data modification, deletion, or execution. While the description is empty, the tool name is explicit enough to classify with high confidence. The severity is low because retrieval of product data poses minimal risk if misused by an AI agent.
From the tool's definition Tool name 'list_products' indicates retrieval of product data with no modification or deletion. No description provided, but the name alone strongly suggests a read operation consistent with the server's advertised 'full store management' capability.
Attacks that exploit this kind of access
list_products. It is categorised as a Read tool in the AdminAgent MCP Server, which means it retrieves data without modifying state.
Register the AdminAgent MCP server in PolicyLayer and add a rule for list_products: 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 AdminAgent. Nothing to install.
list_products 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_products 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_products. 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_products is provided by the AdminAgent MCP server (rushikeshmore/admin-agent). 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 →