prepare_native_stake_delegate

SERVERVaultPilot MCP SOURCEvaultpilot-mcp

High RISK CLASS

Category Execute

Parameters 33 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-szhygulin-vaultpilot-mcp/prepare-native-stake-delegate.md

WHAT IT DOES

What prepare_native_stake_delegate does on VaultPilot MCP

AI agents invoke prepare_native_stake_delegate 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	Solana wallet that funds the stake account and becomes its staker + withdrawer authority. Must have an initialized durable-nonce account (prepare_solana_nonce_i
`amountSol`	string	Yes	Human-readable SOL amount to stake (e.g. "1.5"). Decimals are SOL-native (9). The actual lamports moved from the wallet are this value PLUS the stake account re
`validator`	string	Yes	Vote-account address (NOT validator identity) of the validator to delegate to. Solana's stake program delegates to vote accounts, which validators publish along

Parameters from the server's own tool schema.

RISK

Why prepare_native_stake_delegate is rated High

While this is financial in nature (staking SOL), the tool itself does not move money directly — it builds an unsigned transaction that the user must sign and broadcast. The execution of that transaction is the financial commitment. The tool's job is to construct and stage that operation. This fits Execute (runs external operations) rather than Financial (direct money movement).

From the tool's definition Tool 'builds' and 'delegates' SOL to validators, creating stake accounts and committing funds to Solana's staking system. This is an external operation that triggers irreversible blockchain state changes once signed and broadcast.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs prepare_native_stake_delegate 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_native_stake_delegate, this is the rule to start with:

prepare_native_stake_delegate Rate-limited

prepare_native_stake_delegate 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "prepare_native_stake_delegate": {
      "limits": [
        {
          "counter": "prepare_native_stake_delegate_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT 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_native_stake_delegate call is checked against it from then on.

FAQ

Questions about prepare_native_stake_delegate

What does the prepare_native_stake_delegate tool do? +

Build an unsigned native-stake-program tx that creates a fresh stake account at a deterministic address (derived per (wallet, validator) via createAccountWithSeed) and delegates it to the given validator vote account. Funds the stake account with amountSol SOL of active principal PLUS a ~0.00228 SOL rent-exempt seed (reclaimable on full withdraw). Authority is the user's wallet for both staker + withdrawer roles — no separate authority handoff is supported in this server. DURABLE NONCE REQUIRED. Refuses if a stake account already exists at the deterministic address (the user almost certainly meant prepare_native_stake_deactivate / withdraw on the existing position). BLIND-SIGN on Ledger by default — match the Message Hash on-device. To pick a validator, call list_solana_validators first. 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.

What parameters does prepare_native_stake_delegate accept? +

prepare_native_stake_delegate accepts 3 parameters: wallet, amountSol, validator. Required: wallet, amountSol, validator. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on prepare_native_stake_delegate? +

Register the VaultPilot MCP server in PolicyLayer and add a rule for prepare_native_stake_delegate: 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_native_stake_delegate? +

prepare_native_stake_delegate is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit prepare_native_stake_delegate? +

Yes. Add a rate_limit block to the prepare_native_stake_delegate 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_native_stake_delegate completely? +

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

prepare_native_stake_delegate 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 → High-risk tools on this server →

Across the catalogue

hook_native_function on Frida Game Hacking MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →