Return a sparse verification artifact for a prepared tx — raw calldata (or TRON rawDataHex), chain, to/value, payloadHash, preSignHash if preview_send has pinned gas, plus a static prompt instructing a second LLM on how to decode the bytes from scratch. Intended for adversarial independent verifi...
AI agents call get_verification_artifact to retrieve information from VaultPilot MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
handle | string | Yes | Opaque handle returned by any prepare_* tool. Returns a sparse, copy-paste-friendly JSON artifact carrying the raw calldata (or TRON rawDataHex), chain, recipie |
Parameters from the server's own tool schema.
Even though get_verification_artifact only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Return a sparse verification artifact for a prepared tx — raw calldata (or TRON rawDataHex), chain, to/value, payloadHash, preSignHash if preview_send has pinned gas, plus a static prompt instructing a second LLM on how to decode the bytes from scratch. Intended for adversarial independent verification: the user copies this artifact into a second LLM session (different provider recommended) so the second agent produces an independent decode with no shared context from the current conversation. If the two decodes disagree — or if the preSignHash doesn't match what Ledger displays at sign time — the user rejects. Does NOT call any external API; read-only in-memory lookup. Output deliberately omits the server's humanDecode, swiss-knife URL, and 4byte cross-check so the second agent cannot echo them. Handles live in-memory for 15 minutes after issue. It is categorised as a Read tool in the VaultPilot MCP MCP Server, which means it retrieves data without modifying state.
get_verification_artifact 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 get_verification_artifact: 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.
get_verification_artifact is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_verification_artifact 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 get_verification_artifact. 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.
get_verification_artifact 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.