Email and SMS campaign management - create, update, send, schedule campaigns
AI agents use campaigns to create or update resources in Brevo MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Brevo MCP Server environment.
This tool primarily performs reversible write operations (create, update, schedule). While 'send' triggers external communication with potential reputational and operational impact, it is not irreversibly destructive of data and could theoretically be mitigated.
From the tool's definition Tool description states: 'create, update, send, schedule campaigns' for email and SMS. The 'send' and 'schedule' actions have significant side effects as they trigger mass communication to recipients.
Attacks that exploit this kind of access
Email and SMS campaign management - create, update, send, schedule campaigns. It is categorised as a Write tool in the Brevo MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Brevo MCP Server MCP server in PolicyLayer and add a rule for campaigns: 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 Brevo MCP Server. Nothing to install.
campaigns 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 campaigns 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 campaigns. 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.
campaigns is provided by the Brevo MCP Server MCP server (samihalawa/brevo-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 →