Search for contacts by name, organization, or notes
AI agents call search_contacts to retrieve information from macOS Contacts MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The search_contacts tool retrieves contact information based on search criteria without modifying, deleting, or executing external operations. This is a standard read operation with minimal security risk—it accesses existing data that the user already has access to through the macOS Contacts app. The blast radius of misuse is low: an AI agent might retrieve unwanted contact information, but cannot alter or delete it.
From the tool's definition Tool description states 'Search for contacts' and sibling tools include create_contact, update_contact, and get_contact, positioning this as a retrieval/query operation. No modification, deletion, or external execution is described.
Documented attack patterns abuse exactly the kind of access search_contacts gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and macOS Contacts MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for search_contacts:
{
"version": "1",
"default": "deny",
"tools": {
"search_contacts": {}
}
} search_contacts is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search for contacts by name, organization, or notes. It is categorised as a Read tool in the macOS Contacts MCP MCP Server, which means it retrieves data without modifying state.
Register the macOS Contacts MCP server in PolicyLayer and add a rule for search_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 macOS Contacts MCP. Nothing to install.
search_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 search_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 search_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.
search_contacts is provided by the macOS Contacts MCP server (jcontini/macos-contacts-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from macOS Contacts MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 macOS Contacts MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.