recommend_for_lesson
AI agents call recommend_for_lesson 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.
The tool appears to retrieve or generate product recommendations for lessons based on the server's stated function of providing recommendations for classroom materials. This is a Read operation (no side effects, no data modification, no execution of external code). Severity is low because misuse would only return irrelevant or unexpected product suggestions without causing data loss or financial impact.
From the tool's definition Tool name 'recommend_for_lesson' and sibling tools like 'search_products', 'get_best_sellers', and 'generate_semester_preparation_list' all indicate recommendation/retrieval operations.
Attacks that exploit this kind of access
recommend_for_lesson. 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 recommend_for_lesson: 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.
recommend_for_lesson 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 recommend_for_lesson 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 recommend_for_lesson. 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.
recommend_for_lesson 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 →