Critical Risk →

sendEvmToken

Send ERC-20 tokens on any supported EVM network (using private key from .env)

How to control sendEvmToken ↓

AI agents use sendEvmToken to commit financial operations through Web3 MCP Server — usually the final step of a payment, billing, or trading workflow. A call moves real money.

Critical Risk

This tool transfers ERC-20 tokens (financial assets) on EVM blockchains using a stored private key. Token transfers are irreversible on-chain and directly move financial value. Misuse could result in permanent loss of funds, making this critical severity under the Financial category.

From the tool's definition Send ERC-20 tokens on any supported EVM network (using private key from .env)

Documented attack patterns abuse exactly the kind of access sendEvmToken gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and Web3 MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for sendEvmToken:

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

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

  1. Create a free account and register Web3 MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
GATE THIS TOOL →

Free to start. No card required.

Go deeper

What does the sendEvmToken tool do? +

Send ERC-20 tokens on any supported EVM network (using private key from .env). It is categorised as a Financial tool in the Web3 MCP Server MCP Server, which means it involves financial transactions. Block by default and require explicit approval.

How do I enforce a policy on sendEvmToken? +

Register the Web3 MCP Server MCP server in PolicyLayer and add a rule for sendEvmToken: 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 Web3 MCP Server. Nothing to install.

What risk level is sendEvmToken? +

sendEvmToken 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 sendEvmToken? +

Yes. Add a rate_limit block to the sendEvmToken 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 sendEvmToken completely? +

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

sendEvmToken is provided by the Web3 MCP Server MCP server (strangelove-ventures/web3-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Web3 MCP Server tool call.

Deterministic rules across all 55 Web3 MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

55 Web3 MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.