Read emails from inbox or specified folder. Supports multiple accounts (QQ, 163, etc.)
AI agents call read_emails to retrieve information from Email MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and reads email content, which is a read-only operation with no direct side effects on data integrity. However, severity is elevated to 'medium' rather than 'low' because email often contains sensitive personal, financial, or confidential information (authentication tokens, passwords, financial statements, proprietary data, etc.).
From the tool's definition Tool name is 'read_emails' and description states 'Read emails from inbox or specified folder.' The action is retrieval without modification.
Attacks that exploit this kind of access
Read emails from inbox or specified folder. Supports multiple accounts (QQ, 163, etc.). It is categorised as a Read tool in the Email MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Email MCP Server MCP server in PolicyLayer and add a rule for read_emails: 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 MCP Server. Nothing to install.
read_emails 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_emails 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_emails. 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_emails is provided by the Email MCP Server MCP server (tianpeijun/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 →