AI agents call search_music to retrieve information from Mcp Apple without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves music data from Apple's search infrastructure without creating, modifying, deleting, or executing any actions. It is a straightforward informational query with no blast radius if misused—worst case, it returns unexpected results or excessive searches.
From the tool's definition Tool name 'search_music' and description 'Search for music on Apple Music/iTunes' indicate a query operation with no side effects. The server description confirms it uses the 'iTunes Search API', which is a read-only search interface.
Attacks that exploit this kind of access
Search for music on Apple Music/iTunes. It is categorised as a Read tool in the Mcp Apple MCP Server, which means it retrieves data without modifying state.
Register the Mcp Apple MCP server in PolicyLayer and add a rule for search_music: 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 Mcp Apple. Nothing to install.
search_music 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_music 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_music. 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_music is provided by the Mcp Apple MCP server (markswendsen-code/mcp-apple). 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 →