AI agents use generate_variants 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.
The tool generates design variants for Vue components, which creates new data artifacts (variant definitions, configurations, or documentation outputs) in a reversible manner. This is a Write operation—it produces outputs that can be modified or deleted, not a Read operation (which would only query existing data) nor an Execute operation (which would run arbitrary code with side effects).
From the tool's definition Tool name 'generate_variants' combined with context showing it works with Vue.js design systems for 'variant generation' and the description 'Analyze a Vue component' indicates it creates or generates new variant outputs (Write operation) rather than merely…
Attacks that exploit this kind of access
Analyze a Vue component. 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_variants: 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_variants 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_variants 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_variants. 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_variants 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 →