AI agents call contacts to retrieve information from Apple MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries contact data without creating, modifying, deleting, or executing any actions. The scope is limited to retrieving existing contact information from the local Apple Contacts app. While contact data may include sensitive PII, the read-only nature and local scope limit the blast radius of misuse to information disclosure rather than system compromise or data destruction.
From the tool's definition Tool name 'contacts' with description 'Search and retrieve contacts from Apple Contacts app' indicates data retrieval only. The verbs 'search' and 'retrieve' denote read-only operations with no modification or execution capability.
Attacks that exploit this kind of access
Search and retrieve contacts from Apple Contacts app. It is categorised as a Read tool in the Apple MCP MCP Server, which means it retrieves data without modifying state.
Register the Apple MCP server in PolicyLayer and add a rule for contacts: 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 Apple MCP. Nothing to install.
contacts 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 contacts 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 contacts. 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.
contacts is provided by the Apple MCP server (obisagno/apple-mcp). 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 →