create_campaign
AI agents use create_campaign to create or update resources in Mailchimp MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mailchimp MCP Server environment.
This tool creates a new campaign, which is a write operation that generates marketing content and potentially sets up email distributions. While reversible (campaigns can be deleted), it represents a high-severity capability because a misused campaign could send unsolicited communications to large audiences, damage sender reputation, or facilitate spam.
From the tool's definition Tool name 'create_campaign' and server context (Mailchimp API for managing campaigns) indicate this creates a new marketing campaign.
Attacks that exploit this kind of access
create_campaign. It is categorised as a Write tool in the Mailchimp MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mailchimp MCP Server MCP server in PolicyLayer and add a rule for create_campaign: 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 Mailchimp MCP Server. Nothing to install.
create_campaign 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 create_campaign 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 create_campaign. 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.
create_campaign is provided by the Mailchimp MCP Server MCP server (mattcoatsworth/mailchip-mcp-server). 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 →