Send an email using transactional email service
AI agents invoke send_transactional_email to trigger actions in Sitecore Send. 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.
Sending a transactional email triggers an external operation (delivering an email to a recipient) that cannot be undone once sent. This falls under Execute rather than Write because it causes a real-world side effect (email delivery) beyond just modifying stored data. Severity is high because a misused agent could send unsolicited or malicious emails to real recipients at scale.
From the tool's definition "Send an email using transactional email service"
Attacks that exploit this kind of access
Send an email using transactional email service. It is categorised as a Execute tool in the Sitecore Send MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Sitecore Send MCP server in PolicyLayer and add a rule for send_transactional_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 Sitecore Send. Nothing to install.
send_transactional_email 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_transactional_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_transactional_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_transactional_email is provided by the Sitecore Send MCP server (izharikov/send-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 →