Transfer native tokens (ETH, MATIC, etc.) to an address. Uses the configured wallet.
AI agents use transfer_native to commit financial operations through EVM MCP Server — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool directly facilitates the movement of cryptocurrency assets, which represents a financial obligation and irreversible asset transfer. An AI agent misusing this tool could drain wallets, send funds to incorrect addresses, or execute unauthorized transactions at scale. Financial is the highest-severity category and takes precedence.
From the tool's definition Tool explicitly transfers native tokens (ETH, MATIC, etc.) to an address using the configured wallet—a direct movement of blockchain-native assets. The description unambiguously describes a financial transaction: 'Transfer native tokens...to an address.'
Documented attack patterns abuse exactly the kind of access transfer_native gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and EVM MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for transfer_native:
{
"version": "1",
"default": "deny",
"tools": {
"transfer_native": {
"deny_if": [
{
"conditions": [],
"on_deny": "Requires human approval."
}
]
}
}
} Any call to transfer_native is blocked until a human approves it. The rest of the server keeps working.
Free to start. No card required.
Transfer native tokens (ETH, MATIC, etc.) to an address. Uses the configured wallet. It is categorised as a Financial tool in the EVM MCP Server MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the EVM MCP Server MCP server in PolicyLayer and add a rule for transfer_native: 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 EVM MCP Server. Nothing to install.
transfer_native is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the transfer_native 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 transfer_native. 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.
transfer_native is provided by the EVM MCP Server MCP server (mcpdotdirect/evm-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from EVM MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
25 EVM MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.