prepare_marginfi_withdraw

SERVERVaultPilot MCP SOURCEvaultpilot-mcp

Critical RISK CLASS

Category Financial

Parameters 62 required

Recommended Approval-gatedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-szhygulin-vaultpilot-mcp/prepare-marginfi-withdraw.md

WHAT IT DOES

What prepare_marginfi_withdraw does on VaultPilot MCP

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

Parameter	Type	Required	Description
`mint`	object	—	Base58 SPL mint address. Used as an override or when the token isn't in the canonical SOLANA_TOKENS table. Exactly one of `symbol` or `mint` must be passed.
`amount`	string	Yes	Human-readable decimal amount to withdraw. Pre-flight refuses if the withdraw would push the health factor below the maintenance threshold.
`symbol`	string	—	Canonical token symbol (USDC, SOL, USDT, JUP, BONK, JTO, mSOL, jitoSOL). The builder resolves this to the underlying mint; MarginFi treats SOL as wSOL internall
`wallet`	string	Yes	Base58 Solana mainnet address (ed25519 pubkey, 43 or 44 chars).
`withdrawAll`	boolean	—	Set true to close the entire supplied position in this bank (lets the SDK pass the `withdraw_all` on-chain flag so the bank clears the balance slot). Omit for p
`accountIndex`	integer	—	MarginfiAccount slot (0 = first, 1 = second, ...). Most users stay on 0. Use a different index to segregate positions across multiple MarginfiAccounts owned by

Parameters from the server's own tool schema.

RISK

Why prepare_marginfi_withdraw is rated Critical

This tool directly moves cryptocurrency assets out of a DeFi lending protocol (MarginFi). While the transaction is unsigned and requires Ledger signing, the tool constructs and commits a financial obligation. The severity is high rather than critical because it requires explicit Ledger hardware signature approval before execution, providing a hardware-based safeguard against unauthorized agent misuse.

From the tool's definition Tool description explicitly states it 'Withdraws the specified amount' from user's MarginFi position and involves DeFi protocol interaction with collateral/health factor logic.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs prepare_marginfi_withdraw 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_marginfi_withdraw, this is the rule to start with:

prepare_marginfi_withdraw Approval-gated

Any call to prepare_marginfi_withdraw 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": {
    "prepare_marginfi_withdraw": {
      "deny_if": [
        {
          "conditions": [],
          "on_deny": "Requires human approval."
        }
      ]
    }
  }
}

GATE THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect VaultPilot MCP, apply this rule, and every prepare_marginfi_withdraw call is checked against it from then on.

FAQ

Questions about prepare_marginfi_withdraw

What does the prepare_marginfi_withdraw tool do? +

Build an unsigned MarginFi WITHDRAW tx. Withdraws the specified amount (or ALL, via withdrawAll: true) from the user's supplied position in the named bank. Pre-flight refuses if the account has zero free collateral (the withdraw would push the health factor below the maintenance threshold — the on-chain tx would revert). DURABLE NONCE + prepare_marginfi_init prerequisites identical to prepare_marginfi_supply. BLIND-SIGN on Ledger. It is categorised as a Financial tool in the VaultPilot MCP MCP Server, which means it involves financial transactions. Block by default and require explicit approval.

What parameters does prepare_marginfi_withdraw accept? +

prepare_marginfi_withdraw accepts 6 parameters: mint, amount, symbol, wallet, withdrawAll, accountIndex. Required: amount, wallet. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on prepare_marginfi_withdraw? +

Register the VaultPilot MCP server in PolicyLayer and add a rule for prepare_marginfi_withdraw: 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.

What risk level is prepare_marginfi_withdraw? +

prepare_marginfi_withdraw 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 prepare_marginfi_withdraw? +

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

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

prepare_marginfi_withdraw 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.

KEEP EXPLORING

More on VaultPilot, and thousands of servers like it.

This server

All 189 VaultPilot tools → Critical-risk tools on this server →

Across the catalogue

build_redeem_withdraw_tx on Atv → All critical-risk MCP tools → The MCP Attack Database →

Guides

Govern MCP payment tools →Human-in-the-loop →Tool call approval →