AI agents call search_tokens 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 retrieves and filters existing design token data without creating, modifying, deleting, or executing any operations. It is a search/query function that returns matching tokens based on criteria, which is characteristic of Read-category operations. The low severity reflects minimal blast radius—misuse would only return unintended token data, not cause destructive or operational harm to the design system.
From the tool's definition Tool performs search operations on design tokens by querying name, category path, value, or description. The verb 'search' combined with the context of 'loading' versus direct retrieval indicates a read-only query operation with no modification or side…
Attacks that exploit this kind of access
Search flattened design tokens by token name, category path, value, or description. Much more practical than loading the full token tree for large systems. 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_tokens: 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_tokens 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_tokens 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_tokens. 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_tokens 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 →