AI agents call list_messages to retrieve information from Mail without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays messages from a folder—a read-only operation. Even in the context of an email server with write/destructive capabilities (delete_messages, delete_folder), this specific tool performs simple enumeration. Severity is low because listing messages carries minimal risk; an agent querying messages in the wrong folder is far less harmful than deleting or sending them.
From the tool's definition Tool name 'list_messages' combined with description 'List messages in a folder' indicates retrieval of message metadata without modification. No side effects, no deletions, no execution, no financial operations.
Attacks that exploit this kind of access
List messages in a folder. It is categorised as a Read tool in the Mail MCP Server, which means it retrieves data without modifying state.
Register the Mail MCP server in PolicyLayer and add a rule for list_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 Mail. Nothing to install.
list_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 list_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 list_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.
list_messages is provided by the Mail MCP server (kpihx/mail-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 →