Send a preview of a campaign to one or more email addresses
AI agents use send_campaign_preview to create or update resources in Campaign Monitor MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Campaign Monitor MCP environment.
The tool performs a write operation by creating and sending email messages. While it uses 'send', it is not destructive (emails can be unsent or ignored) and does not execute arbitrary code or move money.
From the tool's definition send_campaign_preview sends a preview of a campaign to email addresses. This creates and transmits email messages (writes/creates data), which is a reversible action that modifies the state of the email system by adding preview messages to recipients' inboxes.
Attacks that exploit this kind of access
Send a preview of a campaign to one or more email addresses. It is categorised as a Write tool in the Campaign Monitor MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Campaign Monitor MCP server in PolicyLayer and add a rule for send_campaign_preview: 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 Campaign Monitor MCP. Nothing to install.
send_campaign_preview 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_campaign_preview 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_campaign_preview. 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_campaign_preview is provided by the Campaign Monitor MCP server (pauliowest/cmon-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 →