send_typing · Wa Bridge MCP: Risk & Policy

WHAT IT DOES

What send_typing does on Wa Bridge

AI agents invoke send_typing to trigger actions in Wa Bridge. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why send_typing needs a policy

Sending a presence/typing indicator is an external side-effecting action on the WhatsApp platform. It doesn't read or write persistent data, but it executes an operation that changes the visible state for other participants. It's not destructive or financial, but it does trigger a real-time external operation, placing it in Execute.

From the tool's definition 'Send a presence indicator' — triggers an external operation on WhatsApp (typing/presence state) that affects what other users see in real time

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_typing Rate-limited

send_typing stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "send_typing": {
      "limits": [
        {
          "counter": "send_typing_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Wa Bridge, so you can run agents against it safely.

FAQ

Questions about send_typing

What does the send_typing tool do? +

Send a presence indicator. State. It is categorised as a Execute tool in the Wa Bridge MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on send_typing? +

Register the Wa Bridge MCP server in PolicyLayer and add a rule for send_typing: 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.

What risk level is send_typing? +

send_typing is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit send_typing? +

Yes. Add a rate_limit block to the send_typing 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.

How do I block send_typing completely? +

Set action: deny in the PolicyLayer policy for send_typing. 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.

What MCP server provides send_typing? +

send_typing 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.