AI agents call get_media_url to retrieve information from Whatsapp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata (a temporary download URL) for an existing media file but does not modify, delete, or execute any operations. It is a pure read operation with minimal risk exposure, even if misused by an agent. The temporary nature of the URLs mitigates information disclosure risk.
From the tool's definition Tool description states 'Get the download URL for an uploaded media file' — a retrieval operation with no side effects. Time-limited URLs (5 minute expiration) further indicate read-only access.
Attacks that exploit this kind of access
Get the download URL for an uploaded media file. URLs expire after 5 minutes. It is categorised as a Read tool in the Whatsapp MCP Server, which means it retrieves data without modifying state.
Register the Whatsapp MCP server in PolicyLayer and add a rule for get_media_url: 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. Nothing to install.
get_media_url 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_url 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_url. 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_url is provided by the Whatsapp MCP server (spirit122/whatsapp-mcp-server). 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 →