AI agents call read_message to retrieve information from Inbox 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 data by reading message content. It has no side effects—it does not create, modify, delete, or execute operations. The action is purely informational. The severity is low because exposure of this tool allows an AI agent to read emails, which is a confidentiality concern but does not enable destructive or irreversible actions.
From the tool's definition Tool name 'read_message' and description 'Read the full body of a specific email by its sequence number' indicate retrieval of email content without modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Read the full body of a specific email by its sequence number. It is categorised as a Read tool in the Inbox MCP Server, which means it retrieves data without modifying state.
Register the Inbox MCP server in PolicyLayer and add a rule for read_message: 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 Inbox. Nothing to install.
read_message 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_message 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_message. 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_message is provided by the Inbox MCP server (p-w-4-z/inbox-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 →