Build an unsigned WETH → native ETH unwrap transaction via a direct WETH.withdraw(uint256) call on the canonical WETH9 contract for the target chain. Supported chains: ethereum, arbitrum, polygon, base, optimism. Pass an explicit decimal amount (e.g. "0.5") or the literal "max" to unwrap the full...
AI agents call prepare_weth_unwrap to permanently remove resources in VaultPilot MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
| Parameter | Type | Required | Description |
|---|---|---|---|
chain | string | — | |
amount | string | Yes | Human-readable WETH amount, NOT raw wei. Example: "0.5" for 0.5 WETH. Pass "max" to unwrap the full WETH balance. WETH is always 18 decimals on every supported |
wallet | string | Yes |
Parameters from the server's own tool schema.
An AI agent that decides to call prepare_weth_unwrap doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from VaultPilot MCP is gone — there is no undo for destructive operations.
Attacks that exploit this kind of access
Build an unsigned WETH → native ETH unwrap transaction via a direct WETH.withdraw(uint256) call on the canonical WETH9 contract for the target chain. Supported chains: ethereum, arbitrum, polygon, base, optimism. Pass an explicit decimal amount (e.g. "0.5") or the literal "max" to unwrap the full WETH balance. WETH is always 18 decimals. No approval is required — the wallet burns its own balance and receives native ETH back in the same call; the call is cheaper than routing through a DEX/aggregator. Balance is checked pre-build and the call refuses with a clear message if the wallet is short, rather than letting the tx revert on-chain. For the symmetric wrap direction (native ETH → WETH), use prepare_native_send with the WETH contract as to — sending ETH to the WETH9 fallback triggers deposit() automatically. It is categorised as a Destructive tool in the VaultPilot MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
prepare_weth_unwrap accepts 3 parameters: chain, amount, wallet. Required: amount, wallet. The full parameter table on this page comes from the server's own tool schema.
Register the VaultPilot MCP server in PolicyLayer and add a rule for prepare_weth_unwrap: 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 VaultPilot MCP. Nothing to install.
prepare_weth_unwrap is a Destructive 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 prepare_weth_unwrap 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 prepare_weth_unwrap. 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.
prepare_weth_unwrap is provided by the VaultPilot MCP server (vaultpilot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.