AI agents call read_messages to retrieve information from Imessage without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical message data from iMessage conversations. While it performs no write/delete/execute operations, the sensitivity is medium due to the personal and potentially confidential nature of message content (private conversations, sensitive information, contacts). An AI agent with unrestricted access could exfiltrate private communications, but the tool itself only reads without side effects.
From the tool's definition Tool name 'read_messages' and description 'Read recent messages from a specific chat' indicate data retrieval with no modification capability. Server is described as 'Read-only MCP server'.
Attacks that exploit this kind of access
Read recent messages from a specific chat, oldest first. It is categorised as a Read tool in the Imessage MCP Server, which means it retrieves data without modifying state.
Register the Imessage MCP server in PolicyLayer and add a rule for read_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. Nothing to install.
read_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 read_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 read_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.
read_messages is provided by the Imessage MCP server (moritzhwnr/imessage-cli). 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 →