search_messages
AI agents call search_messages 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.
The tool searches messages within iMessage, which retrieves data without modification. The server's explicit 'Read-only' designation and the context of sibling read-only tools confirm this is a Read operation. Confidence is 0.75 rather than higher due to empty tool description, but the server-level read-only constraint and naming convention provide strong contextual evidence.
From the tool's definition Server is described as 'Read-only access to imessage' and sibling tools include 'get_conversation', 'get_recent_messages', 'list_conversations', 'list_unreplied' which are all read operations. Tool name 'search_messages' follows this read-only pattern.
Attacks that exploit this kind of access
search_messages. It is categorised as a Read tool in the Imessage-MCP MCP Server, which means it retrieves data without modifying state.
Register the Imessage- 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. 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 (joshkaplan-dev/imessage-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 →