Low Risk

get_handles

Get list of all contacts/handles (phone numbers, email addresses) that have sent or received iMessages. Returns handle IDs that can be used with

How to control get_handles ↓

AI agents call get_handles to retrieve information from iMessage MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Even though get_handles only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

Documented attack patterns abuse exactly the kind of access get_handles gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and iMessage MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for get_handles:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_handles": {}
  }
}

get_handles is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register iMessage MCP — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the get_handles tool do? +

Get list of all contacts/handles (phone numbers, email addresses) that have sent or received iMessages. Returns handle IDs that can be used with. It is categorised as a Read tool in the iMessage MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_handles? +

Register the iMessage MCP server in PolicyLayer and add a rule for get_handles: 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 iMessage MCP. Nothing to install.

What risk level is get_handles? +

get_handles is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_handles? +

Yes. Add a rate_limit block to the get_handles 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.

How do I block get_handles completely? +

Set action: deny in the PolicyLayer policy for get_handles. 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.

What MCP server provides get_handles? +

get_handles is provided by the iMessage MCP server (wyattjoh/imessage-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every iMessage MCP tool call.

Deterministic rules across all 6 iMessage MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

6 iMessage MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.