AI agents use add_contact to create or update resources in Wati — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Wati environment.
The 'add_contact' tool creates or adds new contact entries to the system. This is a reversible write operation (contacts can be modified or removed later). It does not execute code, delete data irreversibly, or move money. The severity is medium because misuse could lead to spam, harassment, or unwanted contact creation, but the blast radius is limited to contact data rather than system-wide or financial impact.
From the tool's definition Tool is named 'add_contact' on a WATI WhatsApp Business API MCP server alongside other contact and message management tools. The name 'add_contact' indicates creation of new contact records.
Attacks that exploit this kind of access
add_contact. It is categorised as a Write tool in the Wati MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Wati MCP server in PolicyLayer and add a rule for add_contact: 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 Wati. Nothing to install.
add_contact 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 add_contact 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 add_contact. 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.
add_contact is provided by the Wati MCP server (jairajmehra/wati_whatsapp_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 →