send-mon · Monad MCP Server MCP: Risk & Policy

WHAT IT DOES

What send-mon does on Monad MCP Server

AI agents use send-mon to commit financial operations through Monad 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-mon needs a policy

This tool transfers MON tokens (cryptocurrency) to another address, which constitutes moving financial/digital assets. This is irreversible on-chain and could result in permanent loss of funds if misused by an AI agent, making it critical severity.

From the tool's definition Send MON tokens to a specified address on Monad testnet

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send-mon Approval-gated

Any call to send-mon 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-mon": {
      "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 Monad MCP Server, so you can run agents against it safely.

FAQ

Questions about send-mon

What does the send-mon tool do? +

Send MON tokens to a specified address on Monad testnet. It is categorised as a Financial tool in the Monad 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-mon? +

Register the Monad MCP Server MCP server in PolicyLayer and add a rule for send-mon: 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 Monad MCP Server. Nothing to install.

What risk level is send-mon? +

send-mon 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-mon? +

Yes. Add a rate_limit block to the send-mon 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-mon completely? +

Set action: deny in the PolicyLayer policy for send-mon. 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-mon? +

send-mon is provided by the Monad MCP Server MCP server (semutireng22/mcp-monad). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.