send_sms · Unosend MCP Server MCP: Risk & Policy

WHAT IT DOES

What send_sms does on Unosend MCP Server

AI agents use send_sms to commit financial operations through Unosend MCP Server — usually the final step of a payment, billing, or trading workflow. A call moves real money.

WHY IT NEEDS A POLICY

Why send_sms needs a policy

This tool directly commits financial obligations by charging the user's wallet per SMS segment sent. It falls squarely in the Financial category as it moves money (deducts from wallet balance) each time it is invoked. Misuse by an AI agent could result in significant unintended charges if messages are sent in bulk or repeatedly.

From the tool's definition Send an SMS message. Charges from wallet at $0.0075 per segment.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_sms Approval-gated

Any call to send_sms is blocked until a human approves it. The rest of the server keeps working.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "send_sms": {
      "deny_if": [
        {
          "conditions": [],
          "on_deny": "Requires human approval."
        }
      ]
    }
  }
}

GATE THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about send_sms

What does the send_sms tool do? +

Send an SMS message. Charges from wallet at $0.0075 per segment. It is categorised as a Financial tool in the Unosend MCP Server MCP Server, which means it involves financial transactions. Block by default and require explicit approval.

How do I enforce a policy on send_sms? +

Register the Unosend MCP Server MCP server in PolicyLayer and add a rule for send_sms: 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 Unosend MCP Server. Nothing to install.

What risk level is send_sms? +

send_sms is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit send_sms? +

Yes. Add a rate_limit block to the send_sms 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_sms completely? +

Set action: deny in the PolicyLayer policy for send_sms. 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_sms? +

send_sms is provided by the Unosend MCP Server MCP server (unosend/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.