prepare_tron_token_send
Build an unsigned TRC-20 transfer transaction (canonical set only: USDT, USDC, USDD, TUSD) via TronGrid's /wallet/triggersmartcontract. Decimals are resolved from the canonical table — unknown TRC-20s are rejected with an explicit error. Default fee_limit is 100 TRX (TronLink/Ledger Live default)...
This record as markdown: /tools/io-github-szhygulin-vaultpilot-mcp/prepare-tron-token-send.md
What prepare_tron_token_send does on VaultPilot MCP
AI agents use prepare_tron_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 | string | Yes | Base58 TRON recipient address (prefix T). |
from | string | Yes | Base58 TRON sender address (prefix T). |
token | string | Yes | Base58 TRC-20 contract address. Phase 2 only supports the canonical set (USDT, USDC, USDD, TUSD); other TRC-20s are rejected. |
amount | string | Yes | Token amount as a human-readable decimal string (decimals are resolved from the canonical table: 6 for USDT/USDC, 18 for USDD/TUSD). |
feeLimitTrx | string | — | Optional fee-limit override in TRX. Defaults to 100 TRX — Ledger Live / TronLink standard. |
Parameters from the server's own tool schema.
Why prepare_tron_token_send is rated Medium
This tool creates a reversible financial transaction (token transfer) rather than executing an irreversible payment. It builds an unsigned transaction that requires separate signing and submission steps via `send_transaction`, making it a Write operation.
From the tool's definition Tool description states: 'Build an unsigned TRC-20 transfer transaction' and 'Returns a preview + opaque handle.
Risk signalsHandles credentials or secrets (token)
Attacks that exploit this kind of access
The rule that runs prepare_tron_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_tron_token_send, this is the rule to start with:
prepare_tron_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.
The button opens the PolicyLayer dashboard: create your workspace, connect VaultPilot MCP, apply this rule, and every prepare_tron_token_send call is checked against it from then on.
Questions about prepare_tron_token_send
Build an unsigned TRC-20 transfer transaction (canonical set only: USDT, USDC, USDD, TUSD) via TronGrid's /wallet/triggersmartcontract. Decimals are resolved from the canonical table — unknown TRC-20s are rejected with an explicit error. Default fee_limit is 100 TRX (TronLink/Ledger Live default); override with feeLimitTrx if energy pricing has moved. Returns a preview + opaque handle. Forward via send_transaction for USB-HID signing on the paired Ledger. USDT renders natively on the TRON app; other TRC-20s may display raw hex on-device (the contract address and amount are still shown, so the user can verify against the preview). 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.
prepare_tron_token_send accepts 5 parameters: to, from, token, amount, feeLimitTrx. Required: to, from, token, amount. 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_tron_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.
prepare_tron_token_send is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the prepare_tron_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.
Set action: deny in the PolicyLayer policy for prepare_tron_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.
prepare_tron_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.
More on VaultPilot, and thousands of servers like it.
This server
Across the catalogue