Search perfumes by name or brand
AI agents call search_perfumes to retrieve information from Blue Perfumery MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The search_perfumes tool performs a read-only operation that queries the perfume collection database to return matching results. It does not create, modify, delete, or execute any actions; it simply retrieves and returns data based on search parameters. This is a classic Read category tool. Severity is low because retrieval of product catalog data poses minimal risk even if misused by an AI agent.
From the tool's definition Tool is described as 'Search perfumes by name or brand' — a query operation that retrieves data without modification or side effects.
Attacks that exploit this kind of access
Search perfumes by name or brand. It is categorised as a Read tool in the Blue Perfumery MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Blue Perfumery MCP Server MCP server in PolicyLayer and add a rule for search_perfumes: 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 Blue Perfumery MCP Server. Nothing to install.
search_perfumes 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 search_perfumes 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 search_perfumes. 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.
search_perfumes is provided by the Blue Perfumery MCP Server MCP server (recepgocmen/blue-perfumery-mcp-server). 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 →