AI agents call get_product_details to retrieve information from Klydo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves product information from a fashion discovery platform. The naming convention and server purpose (search and discover fashion products) indicate a read-only operation that fetches details without modifying, creating, or deleting data.
From the tool's definition Tool name 'get_product_details' and server context (fashion discovery platform) indicate data retrieval. Description is empty, but the name and sibling tools (get_trending, search_products) all suggest query/fetch operations with no side effects.
Attacks that exploit this kind of access
get_product_details. It is categorised as a Read tool in the Klydo MCP Server, which means it retrieves data without modifying state.
Register the Klydo MCP server in PolicyLayer and add a rule for get_product_details: 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 Klydo. Nothing to install.
get_product_details 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_details 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_details. 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_details is provided by the Klydo MCP server (myselfshravan/klydo-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 →