Send media (image, video, document, audio) via WhatsApp.
AI agents use send_media to create or update resources in Mcp Whatsapp Web — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Whatsapp Web environment.
This tool sends media content to WhatsApp contacts or groups. It creates new messages with media attachments, which is a Write operation. Severity is high because an AI agent could misuse it to send unsolicited or malicious media to arbitrary contacts or groups, potentially causing reputational, legal, or privacy harm at scale.
From the tool's definition Send media (image, video, document, audio) via WhatsApp
Documented attack patterns abuse exactly the kind of access send_media gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Whatsapp Web, and nothing reaches the server without passing your rules. This is the rule we recommend for send_media:
{
"version": "1",
"default": "deny",
"tools": {
"send_media": {
"limits": [
{
"counter": "send_media_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} send_media stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Send media (image, video, document, audio) via WhatsApp. It is categorised as a Write tool in the Mcp Whatsapp Web MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Whatsapp Web MCP server in PolicyLayer and add a rule for send_media: 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 Mcp Whatsapp Web. Nothing to install.
send_media 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_media 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_media. 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_media is provided by the Mcp Whatsapp Web MCP server (mario-andreschak/mcp-whatsapp-web). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Whatsapp Web, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
16 Mcp Whatsapp Web tools catalogued and risk-classified — across an index of 43,000+ MCP servers.