Search Sephora for beauty products. Returns product names, brands, prices, ratings, and URLs. Use this to discover products before viewing details or adding to basket.
AI agents call sephora_search_products to retrieve information from Sephora MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries and returns product information without creating, modifying, deleting, or executing any operations. It is purely informational, allowing discovery of products before further actions. The low severity reflects minimal risk from misuse—an AI agent querying product data poses no financial, destructive, or operational harm.
From the tool's definition Tool name 'sephora_search_products' and description state it 'Search[es] Sephora for beauty products' and 'Returns product names, brands, prices, ratings, and URLs.' This is a retrieval operation with no side effects.
Attacks that exploit this kind of access
Search Sephora for beauty products. Returns product names, brands, prices, ratings, and URLs. Use this to discover products before viewing details or adding to basket. It is categorised as a Read tool in the Sephora MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Sephora MCP Server MCP server in PolicyLayer and add a rule for sephora_search_products: 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 Sephora MCP Server. Nothing to install.
sephora_search_products 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 sephora_search_products 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 sephora_search_products. 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.
sephora_search_products is provided by the Sephora MCP Server MCP server (markswendsen-code/mcp-sephora). 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 →