AI agents call get_media to retrieve information from WhatsApp Cloud API MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The get_media tool retrieves or queries media data from WhatsApp without modifying, creating, deleting, or executing operations. This is a Read operation. Severity is low because media retrieval from a messaging platform has minimal blast radius—it accesses existing data that the authenticated user should already have permission to view.
From the tool's definition Tool name is 'get_media' which indicates retrieval of media content. Description is empty, but the sibling tools (send_template_message, send_text_message) and server description context ('retrieve media through the WhatsApp Cloud API') confirm this is a…
Documented attack patterns abuse exactly the kind of access get_media gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and WhatsApp Cloud API MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_media:
{
"version": "1",
"default": "deny",
"tools": {
"get_media": {}
}
}get_media is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
get_media. It is categorised as a Read tool in the WhatsApp Cloud API MCP Server MCP Server, which means it retrieves data without modifying state.
Register the WhatsApp Cloud API MCP Server MCP server in PolicyLayer and add a rule for get_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 WhatsApp Cloud API MCP Server. Nothing to install.
get_media is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_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 get_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.
get_media is provided by the WhatsApp Cloud API MCP Server MCP server (mmarqueti/whatsapp-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from WhatsApp Cloud API MCP Server, 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.
4 WhatsApp Cloud API MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.