Fetch full email content (headers + body) by IDs from pollEmails. Attachments auto-saved to /tmp/email_mcp_attachments/<id>/. Call pollEmails first.
AI agents call getEmailsById to retrieve information from MCP Email Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves email data without side effects. While emails may contain sensitive information, the tool itself only performs a read operation. The automatic attachment extraction to /tmp/ is a passive storage action, not a destructive or execute operation. Severity is low because reading emails has limited blast radius compared to send, delete, or financial operations on the same server.
From the tool's definition Tool description states 'Fetch full email content (headers + body) by IDs' and 'Call pollEmails first', indicating retrieval only. No modification, deletion, or execution capabilities mentioned.
Attacks that exploit this kind of access
Fetch full email content (headers + body) by IDs from pollEmails. Attachments auto-saved to /tmp/email_mcp_attachments/<id>/. Call pollEmails first. It is categorised as a Read tool in the MCP Email Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Email Server MCP server in PolicyLayer and add a rule for getEmailsById: 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 Email Server. Nothing to install.
getEmailsById 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 getEmailsById 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 getEmailsById. 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.
getEmailsById is provided by the MCP Email Server MCP server (ptbsare/email-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
getEmailsById is one line of MCP Email Server's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →