AI agents call pattern_info to retrieve information from Clo3d without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns pattern piece metadata (outline lines, etc.) without creating, modifying, deleting, or executing operations. It is a read-only information retrieval operation with minimal security risk even if misused by an AI agent, as it cannot alter garment designs, financial systems, or external state.
From the tool's definition Tool name 'pattern_info' and description 'Get a pattern piece's information as JSON' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Get a pattern piece's information as JSON (outline lines, etc.). It is categorised as a Read tool in the Clo3d MCP Server, which means it retrieves data without modifying state.
Register the Clo3d MCP server in PolicyLayer and add a rule for pattern_info: 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 Clo3d. Nothing to install.
pattern_info 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 pattern_info 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 pattern_info. 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.
pattern_info is provided by the Clo3d MCP server (lilbonner/clo3d-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
pattern_info is one line of Clo3d's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →