AI agents use send_media to create or update resources in Wa Bridge — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Wa Bridge environment.
This tool creates new messages in WhatsApp conversations, which is a reversible write operation. While it modifies the state of conversations by adding messages, these actions can be undone (messages can be deleted).
From the tool's definition The tool description explicitly states it "Send[s] a media message" to WhatsApp, which creates/posts new data. It accepts media_url or media_base64 and is documented as a communication action.
Attacks that exploit this kind of access
Send a media message (image, video, audio, or document). Supply the file via either media_url (server fetches it) or media_base64. Confirm with the user before sending. It is categorised as a Write tool in the Wa Bridge MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Wa Bridge 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 Wa Bridge. 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 Wa Bridge MCP server (obirimensah05/whatsapp-bridge). 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 →