AI agents call recommend_components 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 is a lookup/suggestion tool that queries a design system database to recommend components matching a user's described UX goal. It has no side effects—it does not create, modify, delete, or execute code. The output is informational guidance to help users select appropriate components from the existing catalog. Misuse would result in irrelevant recommendations at worst, posing minimal security risk.
From the tool's definition Tool is described as providing 'component recommendation' based on user intent/goals. It retrieves and suggests existing components from the design system without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Intent-oriented component recommendation. Useful when the user describes a task or UX goal rather than knowing exact component names. 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 recommend_components: 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.
recommend_components 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 recommend_components 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 recommend_components. 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.
recommend_components 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 →