get_nft_listings
Issue #569. Ranked individual listings (currently active asks) for a single EVM NFT collection on a single chain, sorted floor-ascending. Distinct from get_nft_collection, which exposes only collection-level metadata (floor / volume / holders) and so cannot ground a 'show me the N cheapest' quest...
This record as markdown: /tools/io-github-szhygulin-vaultpilot-mcp/get-nft-listings.md
What get_nft_listings does on VaultPilot MCP
AI agents call get_nft_listings to retrieve information from VaultPilot MCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
chain | string | — | EVM chain the collection is deployed on. Defaults to ethereum. |
limit | integer | — | Max ranked listings to return (cheapest-first). Capped at 10 — small enough that the agent can validate every row index against the response before referencing |
contractAddress | string | Yes | EVM contract address of the NFT collection. |
Parameters from the server's own tool schema.
Why get_nft_listings is rated Low
This is a pure data retrieval operation that reads NFT market data and metadata. It has no side effects, does not modify state, does not execute code or transactions, and cannot cause financial harm through its own operation. The severity is low because misuse would only expose market information that is already publicly available on blockchain explorers and NFT marketplaces.
From the tool's definition Tool retrieves 'Ranked individual listings (currently active asks)' and 'Returns rows with `tokenId`, `priceEth` / `priceUsd`...' — it queries and retrieves data about NFT listings from Reservoir API with no modification or execution capability.
Attacks that exploit this kind of access
The rule that runs get_nft_listings 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 get_nft_listings, this is the rule to start with:
get_nft_listings is read-only, so it stays allowed. 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 get_nft_listings call is checked against it from then on.
Questions about get_nft_listings
Issue #569. Ranked individual listings (currently active asks) for a single EVM NFT collection on a single chain, sorted floor-ascending. Distinct from get_nft_collection, which exposes only collection-level metadata (floor / volume / holders) and so cannot ground a 'show me the N cheapest' question. Source: Reservoir /orders/asks/v5?status=active&sortBy=price&sortDirection=asc. Returns rows with tokenId, priceEth / priceUsd, priceCurrency, listingSource (marketplace domain — opensea.io / blur.io / x2y2.io / etc.), makerAddress (seller), validUntil (expiry), and orderKind (seaport-v1.6 / blur / etc.). Page size schema-capped at 10 (default 5) — small enough that the agent can validate every referenced row exists in the response. Single-token criteria only; collection-bid criteria orders are filtered out so every row names a concrete tokenId. SCOPE: read-only display tool. VaultPilot does NOT yet expose an NFT-buy preparation flow — Seaport / blur / x2y2 marketplace fills require EIP-712 typed-data signing, gated on the typed-data clear-sign defenses tracked at #453. Use these rows for research / candidate selection; execute any actual buy via the listing's marketplace UI (listingSource field) until the prepare flow lands. AGENT BEHAVIOR: do NOT extrapolate beyond rows.length. Validate that any rows[i] referenced in the answer actually exists in this response. The small page cap is the fabrication-resistance guard called out in #569. EVM-only in v1; Solana NFT marketplaces (Magic Eden / Tensor) 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_listings accepts 3 parameters: chain, limit, contractAddress. Required: contractAddress. 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_listings: 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_listings 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_listings 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_listings. 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_listings 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