send_message
Send an email from the mailbox. Requires a message token with messages:send scope. Both TREKMAIL_ALLOW_SENDING=true and confirm_send=true are required as safety gates. The message is queued for delivery and a message_id is returned immediately.
This record as markdown: /tools/trekmail-mcp-server/send-message.md
What send_message does on TrekMail MCP Server
AI agents invoke send_message to trigger actions in TrekMail MCP Server. 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 send_message is rated High
Sending an email is an external operation with real-world effects (messages delivered to recipients) that cannot be recalled or undone once queued. It spans Write and Execute, but because it triggers an external operation (email delivery to third parties) with potentially irreversible consequences (phishing, spam, data exfiltration, social engineering), Execute is the most appropriate category.
From the tool's definition 'Send an email from the mailbox' and 'The message is queued for delivery and a message_id is returned immediately' — triggers external email delivery operation
Attacks that exploit this kind of access
The rule that runs send_message safely
PolicyLayer is an MCP gateway: it sits between your AI agents and TrekMail MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For send_message, this is the rule to start with:
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 TrekMail MCP Server, apply this rule, and every send_message call is checked against it from then on.
Questions about send_message
Send an email from the mailbox. Requires a message token with messages:send scope. Both TREKMAIL_ALLOW_SENDING=true and confirm_send=true are required as safety gates. The message is queued for delivery and a message_id is returned immediately. It is categorised as a Execute tool in the TrekMail MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the TrekMail MCP Server MCP server in PolicyLayer and add a rule for 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 TrekMail MCP Server. Nothing to install.
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 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 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.
send_message is provided by the TrekMail MCP Server MCP server (trekmail/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on TrekMail MCP Server, and thousands of servers like it.
Across the catalogue