AI agents call search_messages to retrieve information from Mcp Imap without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries email data based on search criteria with no side effects. It does not create, modify, delete, execute code, or move money. It is a classic Read operation with minimal risk, though access to email contents carries some sensitivity depending on what an agent might learn from search results.
From the tool's definition Tool name is 'search_messages' and description states it 'Search messages in a folder by criteria (subject, from, since date, unseen only)' — a query operation that retrieves matching emails without modification or deletion.
Attacks that exploit this kind of access
Search messages in a folder by criteria (subject, from, since date, unseen only). It is categorised as a Read tool in the Mcp Imap MCP Server, which means it retrieves data without modifying state.
Register the Mcp Imap 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 Mcp Imap. 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 Mcp Imap MCP server (ngcdan/mcp-imap-server). 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 →