WhatsApp messaging - send messages, manage campaigns and templates
AI agents use whatsapp 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 creates and modifies messaging campaigns and templates in WhatsApp, which are reversible write operations. While it sends messages (an external communication action), the primary capabilities are creating/updating campaigns and templates rather than executing arbitrary code or triggering unpredictable side effects.
From the tool's definition Tool description states 'send messages, manage campaigns and templates' — direct creation and modification of messaging content and campaign configurations.
Attacks that exploit this kind of access
WhatsApp messaging - send messages, manage campaigns and templates. 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 whatsapp: 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.
whatsapp 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 whatsapp 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 whatsapp. 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.
whatsapp 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 →