Return catalog statistics: total count and average price.
AI agents call get_statistics to retrieve information from Product Management MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves aggregate statistics from the product catalog without any side effects. It does not create, modify, delete, or execute arbitrary operations. The blast radius of misuse is minimal (an agent could retrieve statistics repeatedly, but this causes no harm). This is clearly a Read category tool with low severity.
From the tool's definition Tool description states it 'Return[s] catalog statistics: total count and average price' — a retrieval operation with no modification, creation, or deletion of data.
Attacks that exploit this kind of access
Return catalog statistics: total count and average price. It is categorised as a Read tool in the Product Management MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Product Management MCP Server MCP server in PolicyLayer and add a rule for get_statistics: 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 Product Management MCP Server. Nothing to install.
get_statistics 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_statistics 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_statistics. 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_statistics is provided by the Product Management MCP Server MCP server (nur1sat/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 →