prepare_token_send

SERVERVaultPilot MCP SOURCEvaultpilot-mcp

Medium RISK CLASS

Category Write

Parameters 54 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-token-send.md

WHAT IT DOES

What prepare_token_send does on VaultPilot MCP

AI agents use prepare_token_send to create or update resources in VaultPilot MCP, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your VaultPilot MCP environment.

Parameter	Type	Required	Description
`to`	object	Yes
`chain`	string	—
`token`	string	Yes
`amount`	string	Yes	Human-readable decimal amount, NOT raw wei/base units. Example: "10" for 10 USDC. Decimals resolved from the token contract. Pass "max" to send the full balance
`wallet`	string	Yes

Parameters from the server's own tool schema.

RISK

Why prepare_token_send is rated Medium

This tool creates (but does not yet execute or finalize) a reversible modification to blockchain state—specifically, an unsigned transaction that transfers ERC-20 tokens. It is Write rather than Execute because the transaction is unsigned and requires additional steps (signing, broadcasting) to take effect.

From the tool's definition Tool description states it 'Build[s] an unsigned ERC-20 transfer transaction' and supports sending amounts including 'the full balance'. The tool constructs token transfer operations that modify blockchain state by moving crypto assets.

Risk signalsHandles credentials or secrets (token)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs prepare_token_send 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_token_send, this is the rule to start with:

prepare_token_send Rate-limited

prepare_token_send stays usable, but capped: an agent stuck in a loop can't make hundreds of changes 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_token_send": {
      "limits": [
        {
          "counter": "prepare_token_send_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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_token_send call is checked against it from then on.

FAQ

Questions about prepare_token_send

What does the prepare_token_send tool do? +

Build an unsigned ERC-20 transfer transaction. Pass amount: "max" to send the full balance (resolved at build time). If the user named the token by symbol, call resolve_token first to disambiguate native-vs-bridged variants (USDC vs USDC.e on Arbitrum/Polygon/Optimism, USDC vs USDbC on Base) and surface the warning to the user before committing to a contract. It is categorised as a Write tool in the VaultPilot MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does prepare_token_send accept? +

prepare_token_send accepts 5 parameters: to, chain, token, amount, wallet. Required: to, token, 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_token_send? +

Register the VaultPilot MCP server in PolicyLayer and add a rule for prepare_token_send: 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_token_send? +

prepare_token_send is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit prepare_token_send? +

Yes. Add a rate_limit block to the prepare_token_send 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_token_send completely? +

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

prepare_token_send 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 →

Across the catalogue

sms_send on Twilio SMS MCP Server →send-draft on Meme MCP Server →mail_send_draft on Apple Apps MCP → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →