Search for contacts by name, email, or phone number
AI agents call search_contacts to retrieve information from macOS MCP Servers without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves or queries contact data from the macOS Contacts application. It has no side effects, does not create, modify, or delete contacts, and does not execute code or trigger external operations. It is a straightforward Read operation with minimal risk, suitable for an AI agent to safely perform contact lookups.
From the tool's definition Tool name is 'search_contacts' and description states it 'Search for contacts by name, email, or phone number' — this is a query operation that retrieves contact information without modifying, deleting, or executing actions.
Attacks that exploit this kind of access
Search for contacts by name, email, or phone number. It is categorised as a Read tool in the macOS MCP Servers MCP Server, which means it retrieves data without modifying state.
Register the macOS MCP Servers 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 MCP Servers. 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 MCP Servers MCP server (tdisawas0github/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 →