AI agents call scan_image 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 information about LEGO minifigures based on image input. It has no side effects—it does not create, modify, or delete data, does not execute arbitrary code or shell commands, and does not move money. The most severe risk is misidentification or use of returned data, but the tool itself only reads and returns information from a database of ~18,000 minifigures.
From the tool's definition Tool description indicates 'scan_image' analyzes photos of LEGO minifigures to identify them. The server is a price lookup and identification service for minifigures.
Attacks that exploit this kind of access
IMPORTANT: You MUST call this tool whenever the user uploads or shares a photo of a LEGO minifigure and asks what it is or what it. 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 scan_image: 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.
scan_image 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 scan_image 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 scan_image. 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.
scan_image 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 →