send_email
Send an email via SMTP over TLS. Requires EMAIL_USER and EMAIL_PASS env vars. Defaults to Gmail SMTP (smtp.gmail.com:465). For Gmail, use an App Password (Google Account → Security → 2-Step Verification → App passwords). Override host/port with EMAIL_SMTP_HOST and EMAIL_SMTP_PORT. Supports plain ...
This record as markdown: /tools/io-github-homenshum-nodebench/send-email.md
What send_email does on Nodebench
AI agents use send_email to create or update resources in Nodebench, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nodebench environment.
Why send_email is rated Medium
Sending email creates new data (messages) in external systems and is reversible (emails can be deleted/unsent in many cases), placing it in Write rather than Execute or Destructive. However, severity is medium rather than low because misuse could enable spam, phishing, or unauthorized communications at scale, potentially affecting many recipients.
From the tool's definition Tool description states "Send an email via SMTP over TLS" — this creates and transmits new email messages, modifying the state of external email systems.
Attacks that exploit this kind of access
The rule that runs send_email safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For send_email, this is the rule to start with:
send_email stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Nodebench, apply this rule, and every send_email call is checked against it from then on.
Questions about send_email
Send an email via SMTP over TLS. Requires EMAIL_USER and EMAIL_PASS env vars. Defaults to Gmail SMTP (smtp.gmail.com:465). For Gmail, use an App Password (Google Account → Security → 2-Step Verification → App passwords). Override host/port with EMAIL_SMTP_HOST and EMAIL_SMTP_PORT. Supports plain text and HTML multipart. It is categorised as a Write tool in the Nodebench MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nodebench MCP server in PolicyLayer and add a rule for send_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 Nodebench. Nothing to install.
send_email is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the send_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 send_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.
send_email is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nodebench, and thousands of servers like it.
This server
Across the catalogue