AI agents invoke sendEmailToCampaign to trigger actions in Mailmodo. 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.
This tool triggers the sending of emails to a campaign audience, which is an external operation with real-world effects (recipients receive emails). It cannot be trivially undone once emails are sent, and misuse could result in spam or unintended mass communications. It falls under Execute as it initiates an external operation rather than simply writing/storing data.
From the tool's definition Trigger and email for email campaign trigger with personalization parameter added to the email template
Attacks that exploit this kind of access
Trigger and email for email campaign trigger with personalization parameter added to the email template. It is categorised as a Execute tool in the Mailmodo MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mailmodo MCP server in PolicyLayer and add a rule for sendEmailToCampaign: 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 Mailmodo. Nothing to install.
sendEmailToCampaign 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 sendEmailToCampaign 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 sendEmailToCampaign. 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.
sendEmailToCampaign is provided by the Mailmodo MCP server (mailmodo/mailmodo-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 →