AI agents call magento_stats to retrieve information from Magector 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 metadata about an existing search index. It performs no modifications, deletions, code execution, or financial operations. The outputs are statistics and configuration information used for verification and monitoring purposes only.
From the tool's definition Tool description states 'Get index statistics — total indexed vectors, embedding dimensions, and database path.' The verb 'get' and the purely informational nature of the outputs (statistics, dimensions, path) indicate read-only retrieval with no side effects.
Attacks that exploit this kind of access
Get index statistics — total indexed vectors, embedding dimensions, and database path. Use this to verify the index is loaded and check its size. It is categorised as a Read tool in the Magector MCP Server, which means it retrieves data without modifying state.
Register the Magector MCP server in PolicyLayer and add a rule for magento_stats: 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 Magector. Nothing to install.
magento_stats 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 magento_stats 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 magento_stats. 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.
magento_stats is provided by the Magector MCP server (magector). 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 →