Send the same text message to up to 300 subscribed Viber users in a single API call. Use for announcements or bulk notifications. Do not use for personalised messages — call send_message individually instead. Partial failures are reported per-receiver. Returns message_token and failed_list.
AI agents use broadcast_message to create or update resources in Viber — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Viber environment.
This tool creates new messages that are persisted in recipient inboxes. While reversible in principle (messages can be deleted), it materially alters user data across a large number of recipients (up to 300). The blast radius of misuse is significant—an attacker could spam all subscribers with malicious content.
From the tool's definition Sends messages to up to 300 users in bulk; description states 'Send the same text message to up to 300 subscribed Viber users' and 'announcements or bulk notifications.' This modifies user state (inbox) and creates new data (messages) at scale.
Attacks that exploit this kind of access
Send the same text message to up to 300 subscribed Viber users in a single API call. Use for announcements or bulk notifications. Do not use for personalised messages — call send_message individually instead. Partial failures are reported per-receiver. Returns message_token and failed_list. It is categorised as a Write tool in the Viber MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Viber MCP server in PolicyLayer and add a rule for broadcast_message: 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 Viber. Nothing to install.
broadcast_message 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 broadcast_message 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 broadcast_message. 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.
broadcast_message is provided by the Viber MCP server (serhiizghama/viber-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 →