get_best_sellers
AI agents call get_best_sellers to retrieve information from Teachermall without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves bestseller product information from the Teachermall catalog without modifying, deleting, or executing code. Even with an empty description, the name and surrounding tools in a shopping/recommendation context point to read-only data retrieval. Confidence is reduced from 0.9 to 0.85 due to lack of explicit description confirming safe read-only behavior.
From the tool's definition Tool name 'get_best_sellers' combined with sibling tools like 'search_products' and 'get_product_details' indicates data retrieval functionality. The empty description prevents confirmation, but context suggests querying product catalogs.
Attacks that exploit this kind of access
get_best_sellers. It is categorised as a Read tool in the Teachermall MCP Server, which means it retrieves data without modifying state.
Register the Teachermall MCP server in PolicyLayer and add a rule for get_best_sellers: 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 Teachermall. Nothing to install.
get_best_sellers 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_best_sellers 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_best_sellers. 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_best_sellers is provided by the Teachermall MCP server (reallygood83/teachermall-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 →