email_send_message
Send a new email message via SMTP
This record as markdown: /tools/io-github-alifanov-scopegate/email-send-message.md
What email_send_message does on ScopeGate
AI agents invoke email_send_message to trigger actions in ScopeGate. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why email_send_message is rated High
Sending an email triggers an external operation (SMTP delivery) that cannot be recalled once dispatched. It does not merely write data to a store — it actively delivers a message to external recipients, making it Execute-level. Misuse by an AI agent could result in phishing, data exfiltration, or reputational harm at scale, warranting high severity.
From the tool's definition "Send a new email message via SMTP"
Attacks that exploit this kind of access
The rule that runs email_send_message safely
PolicyLayer is an MCP gateway: it sits between your AI agents and ScopeGate, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For email_send_message, this is the rule to start with:
email_send_message stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect ScopeGate, apply this rule, and every email_send_message call is checked against it from then on.
Questions about email_send_message
Send a new email message via SMTP. It is categorised as a Execute tool in the ScopeGate MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ScopeGate MCP server in PolicyLayer and add a rule for email_send_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 ScopeGate. Nothing to install.
email_send_message is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the email_send_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 email_send_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.
email_send_message is provided by the ScopeGate MCP server (https://mcp.scopegate.cloud/{api_key}). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on ScopeGate, and thousands of servers like it.
Across the catalogue