AI agents call get_theme_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 tool retrieves and queries data from a LEGO minifigure database filtered by theme. It has no side effects, does not modify any data, and poses minimal risk if misused by an AI agent. The worst-case scenario is retrieving unwanted data, which is low severity.
From the tool's definition Tool name 'get_theme_minifigures' and description 'List LEGO minifigures for a theme with prices' indicate data retrieval only. The action is to list and query existing LEGO minifigure data with pricing information.
Attacks that exploit this kind of access
List LEGO minifigures for a theme with prices. Themes: ${ALL_THEMES.join(. 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 get_theme_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.
get_theme_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 get_theme_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 get_theme_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.
get_theme_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 →