AI agents use generate_catalog to create or update resources in Musea — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Musea environment.
This tool generates a new document (a Markdown catalog) from existing design system data. It is a write operation because it creates/produces data output, but it is non-destructive and reversible—the catalog can be regenerated or deleted without permanent damage. It does not execute code, delete data, or move money.
From the tool's definition Tool 'generate_catalog' produces/creates a Markdown catalog document as output. The description states it will 'Produce a single Markdown catalog', indicating document creation or generation.
Attacks that exploit this kind of access
Produce a single Markdown catalog covering every component in the design system, grouped by category. It is categorised as a Write tool in the Musea MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Musea MCP server in PolicyLayer and add a rule for generate_catalog: 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 Musea. Nothing to install.
generate_catalog is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the generate_catalog 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 generate_catalog. 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.
generate_catalog is provided by the Musea MCP server (@vizejs/musea-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 →