AI agents call search_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.
The search_components tool queries and retrieves information about Vue.js components without creating, modifying, deleting, or executing code. It is a pure read operation that returns ranked search results. The low severity reflects that misuse (e.g., searching for sensitive patterns) has minimal blast radius in a design system context where component metadata is typically non-sensitive.
From the tool's definition Tool performs 'full-text search' over component metadata (titles, descriptions, categories, tags, names). This is a retrieval operation with no data modification or side effects.
Attacks that exploit this kind of access
Ranked full-text search over component titles, descriptions, categories, tags, component names, and variant 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 search_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.
search_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 search_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 search_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.
search_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 →