prepare_lido_unstake
Build an unsigned Lido withdrawal request transaction. Wraps requestWithdrawals on the Lido Withdrawal Queue and includes an approve step if needed.
This record as markdown: /tools/io-github-szhygulin-vaultpilot-mcp/prepare-lido-unstake.md
What prepare_lido_unstake does on VaultPilot MCP
AI agents invoke prepare_lido_unstake to trigger actions in VaultPilot MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
wallet | string | Yes | |
amountStETH | string | Yes | Human-readable stETH amount, NOT raw wei. Example: "0.5" for 0.5 stETH (18 decimals). |
approvalCap | string | — | Cap on the ERC-20 approval preceding this action. Omit for "unlimited" (standard DeFi UX — fewer follow-up approvals). Pass "exact" to approve only what this ac |
Parameters from the server's own tool schema.
Why prepare_lido_unstake is rated High
This tool constructs and triggers a transaction on the Lido protocol to request unstaking of staked ETH. Although the transaction is unsigned (requiring manual approval), the tool executes code that interacts with smart contracts and initiates a financial operation whose effects depend on execution.
From the tool's definition 'Build an unsigned Lido withdrawal request transaction' that 'Wraps requestWithdrawals on the Lido Withdrawal Queue' — this executes a blockchain transaction that initiates a DeFi withdrawal operation with external effects.
Attacks that exploit this kind of access
The rule that runs prepare_lido_unstake safely
PolicyLayer is an MCP gateway: it sits between your AI agents and VaultPilot MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For prepare_lido_unstake, this is the rule to start with:
prepare_lido_unstake stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect VaultPilot MCP, apply this rule, and every prepare_lido_unstake call is checked against it from then on.
Questions about prepare_lido_unstake
Build an unsigned Lido withdrawal request transaction. Wraps requestWithdrawals on the Lido Withdrawal Queue and includes an approve step if needed. It is categorised as a Execute tool in the VaultPilot MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
prepare_lido_unstake accepts 3 parameters: wallet, amountStETH, approvalCap. Required: wallet, amountStETH. 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_lido_unstake: 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_lido_unstake is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the prepare_lido_unstake 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_lido_unstake. 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_lido_unstake 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.
More on VaultPilot, and thousands of servers like it.
Across the catalogue