AI agents call get_variant to retrieve information from Musea without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves variant metadata and templates from a design system component library. It performs a read-only lookup operation without side effects, aligning with the Read category definition of 'retrieves or queries data; no side effects'.
From the tool's definition Tool description states 'Retrieve a single variant' with 'resolving the component by path, title, component name, or fuzzy query' — pure data retrieval with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Retrieve a single variant (template and metadata) from a component, resolving the component by path, title, component name, or fuzzy query. It is categorised as a Read tool in the Musea MCP Server, which means it retrieves data without modifying state.
Register the Musea MCP server in PolicyLayer and add a rule for get_variant: 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.
get_variant 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_variant 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_variant. 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_variant 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 →