Recent NFT activity for a wallet across one or more supported EVM chains: mints, sales, transfers, listings (asks), bids, and cancels. Source: Reservoir's /users/{user}/activity/v6. Multi-chain results are merged + sorted by timestamp descending; capped at limit (default 25, max 100). Mirrors get...
AI agents call get_nft_history 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 |
|---|---|---|---|
limit | integer | — | Max merged items to return (newest-first). Default 25, capped at 100 to keep the cross-chain merge bounded. |
chains | array | — | Subset of supported EVM chains to scan. Omit for all five. Multi-chain results are merged + sorted desc by timestamp. |
wallet | string | Yes |
Parameters from the server's own tool schema.
Even though get_nft_history 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
Recent NFT activity for a wallet across one or more supported EVM chains: mints, sales, transfers, listings (asks), bids, and cancels. Source: Reservoir's /users/{user}/activity/v6. Multi-chain results are merged + sorted by timestamp descending; capped at limit (default 25, max 100). Mirrors get_transaction_history's shape but limited to NFT-relevant events — same agent ergonomics, scoped to the NFT side of the wallet. EVM-only in v1; Solana deferred. Read-only. It is categorised as a Read tool in the VaultPilot MCP MCP Server, which means it retrieves data without modifying state.
get_nft_history accepts 3 parameters: limit, chains, wallet. Required: wallet. 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_nft_history: 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_nft_history 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_nft_history 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_nft_history. 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_nft_history 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.