Solana-only: finalize a prepared Solana tx for signing by fetching a FRESH recent blockhash, serializing the message bytes, and computing the base58(sha256(...)) Message Hash the Ledger Solana app will display on blind-sign. MUST be called between prepare_solana_* and send_transaction — Solana bl...
AI agents use preview_solana_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 |
|---|---|---|---|
handle | string | Yes | Opaque handle returned by prepare_solana_native_send / prepare_solana_spl_send. preview_solana_send fetches a fresh Solana blockhash, serializes the message byt |
Parameters from the server's own tool schema.
An AI agent can call preview_solana_send faster than any human can review — one bad instruction and it creates or modifies resources in VaultPilot MCP by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Solana-only: finalize a prepared Solana tx for signing by fetching a FRESH recent blockhash, serializing the message bytes, and computing the base58(sha256(...)) Message Hash the Ledger Solana app will display on blind-sign. MUST be called between prepare_solana_* and send_transaction — Solana blockhashes expire after ~150 blocks (~60s), and the prepare → user-approve → broadcast path on a live Ledger routinely runs longer than that. Splitting the blockhash pin off prepare lets the user see-and-match the hash seconds before tapping Approve, with the full ~60s window available for the broadcast. Returns the pinned UnsignedSolanaTx (messageBase64 + ledger Message Hash) plus the CHECKS PERFORMED agent-task block the agent must auto-run. Re-callable on the same handle: re-calling overwrites the prior pin with a newer blockhash (useful if the user pauses between preview and send). send_transaction will throw a clear error if called without a prior preview_solana_send. 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.
preview_solana_send accepts 1 parameter: handle. Required: handle. 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 preview_solana_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.
preview_solana_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 preview_solana_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 preview_solana_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.
preview_solana_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.