mail_export_email
AI agents call mail_export_email to retrieve information from Pyfastmail without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name suggests exporting (reading/retrieving) email data, which would be a Read operation. However, with no description, we cannot confirm whether it has side effects. Export operations typically read and serialize data, so Read is the most likely category. Severity is medium because exporting email could expose sensitive data at scale. Confidence is low due to the empty description.
From the tool's definition Tool name is 'mail_export_email'; description is empty or uninformative.
Attacks that exploit this kind of access
mail_export_email. It is categorised as a Read tool in the Pyfastmail MCP Server, which means it retrieves data without modifying state.
Register the Pyfastmail MCP server in PolicyLayer and add a rule for mail_export_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 Pyfastmail. Nothing to install.
mail_export_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 mail_export_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 mail_export_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.
mail_export_email is provided by the Pyfastmail MCP server (pjosols/pyfastmail-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 →