AI agents call search_minifigures to retrieve information from Brickem without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a search/lookup function that retrieves information about LEGO minifigures from a database. It has no side effects, does not execute code, does not modify data, and does not commit financial transactions. The only minor risk is information disclosure, but the data is intended to be publicly queryable. Severity is low because misuse would only return product information.
From the tool's definition Tool performs 'Fuzzy search' and 'Returns top 10 matches with prices' — a query operation retrieving data from a minifigure catalogue with no modification, deletion, or execution of external code.
Attacks that exploit this kind of access
Fuzzy search LEGO minifigures by name with optional theme filter. Returns top 10 matches with prices. Good for finding minifigures when you only know part of the name. It is categorised as a Read tool in the Brickem MCP Server, which means it retrieves data without modifying state.
Register the Brickem MCP server in PolicyLayer and add a rule for search_minifigures: 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 Brickem. Nothing to install.
search_minifigures 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_minifigures 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_minifigures. 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_minifigures is provided by the Brickem MCP server (michiganbricks/brickem-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 →