AI agents call search-messages to retrieve information from iMessage MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the local macOS iMessage database to find messages matching search criteria. It performs read-only operations without modifying, deleting, or executing code. However, severity is elevated to 'medium' rather than 'low' because iMessage conversations often contain sensitive personal and financial information, authentication credentials, or private communications.
From the tool's definition Tool name 'search-messages' and description 'Search for messages containing specific text' indicate data retrieval with no modification or side effects. Server description emphasizes 'reading, searching' as core functions.
Documented attack patterns abuse exactly the kind of access search-messages gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and iMessage MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search-messages:
{
"version": "1",
"default": "deny",
"tools": {
"search-messages": {}
}
}search-messages 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 messages containing specific text. It is categorised as a Read tool in the iMessage MCP Server MCP Server, which means it retrieves data without modifying state.
Register the iMessage MCP Server MCP server in PolicyLayer and add a rule for search-messages: 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 Server. Nothing to install.
search-messages 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-messages 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-messages. 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-messages is provided by the iMessage MCP Server MCP server (sameelarif/imessage-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from iMessage MCP Server, 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.
14 iMessage MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.