Fetch a product
AI agents call get_product_by_id to retrieve information from E-commerce MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves product data by ID with no side effects. It performs a standard read operation (GET-like) against the e-commerce database. No data is created, modified, deleted, or executed. The scope is limited to retrieving a single product record, minimizing blast radius if misused.
From the tool's definition Tool description states 'Fetch a product' which is a retrieval operation. Name 'get_product_by_id' indicates a simple read/query operation.
Attacks that exploit this kind of access
Fetch a product. It is categorised as a Read tool in the E-commerce MCP Server MCP Server, which means it retrieves data without modifying state.
Register the E-commerce MCP Server MCP server in PolicyLayer and add a rule for get_product_by_id: 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 E-commerce MCP Server. Nothing to install.
get_product_by_id 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_product_by_id 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_product_by_id. 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_product_by_id is provided by the E-commerce MCP Server MCP server (preetash88/custom-ecommerce-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 →