Envia uma mensagem de vídeo atraves da Zappaz API
AI agents use send_video_message to create or update resources in Zappaz MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zappaz MCP Server environment.
This tool sends a video message via WhatsApp. It creates/delivers a new message to a recipient, which is a reversible write operation (the message can be deleted). The blast radius is medium — an agent could send unsolicited or malicious video content to WhatsApp contacts, but it does not delete data or move money.
From the tool's definition Envia uma mensagem de vídeo atraves da Zappaz API (sends a video message via the Zappaz API)
Attacks that exploit this kind of access
Envia uma mensagem de vídeo atraves da Zappaz API. It is categorised as a Write tool in the Zappaz MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Zappaz MCP Server MCP server in PolicyLayer and add a rule for send_video_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 Zappaz MCP Server. Nothing to install.
send_video_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 send_video_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 send_video_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.
send_video_message is provided by the Zappaz MCP Server MCP server (viiniolliveira/zappaz-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 →