AI agents call read_email to retrieve information from Email without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries email content without any side effects. It does not create, modify, delete, or execute any actions. The read-only nature and explicit 'Read' verb in both name and description clearly place it in the Read category with low severity, as the worst outcome is unauthorized information disclosure from emails the agent already has access to.
From the tool's definition Tool name is 'read_email' and description states 'Read the full content of an email by its EntryID' — explicitly a read operation with no modification or deletion capability.
Attacks that exploit this kind of access
Read the full content of an email by its EntryID. It is categorised as a Read tool in the Email MCP Server, which means it retrieves data without modifying state.
Register the Email MCP server in PolicyLayer and add a rule for read_email: 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 Email. Nothing to install.
read_email 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_email 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_email. 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_email is provided by the Email MCP server (kerodkibatu/email-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 →