Reservoir MCP for AI. Aggregate all NFT liquidity and metadata instantly.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
How this MCP server connects to your AI agent
Reservoir (NFT Liquidity API) gives your AI agent real-time access to NFT market data across multiple major marketplaces. It aggregates active bids, asks, token metadata, and collection stats from platforms like OpenSea, LooksRare, and X2Y2 into a single stream.
You can use this server to compare prices instantly, track floor prices for specific collections, or generate the transaction details needed to buy or sell an NFT directly via your client.
What AI agents can do with Reservoir (NFT Liquidity API) Automation
Execute buy
Generates the required transaction payload needed to buy an NFT.
Execute sell
Creates a transaction payload to accept a pending offer (fill a bid).
Get collection
Fetches metadata and real-time stats for an entire NFT collection.
Pull active buy bids and sell asks from multiple marketplaces (e.g., checking both OpenSea and LooksRare) using list_asks and list_bids.
Get real-time stats for any NFT collection, including its floor price, volume, and metadata, via the get_collection tool.
Retrieve deep information—like rarity or history—for a single token using get_token.
Search for collections by name or contract address (search_collections), or list all tokens held by an owner with filters (list_tokens).
Generate the necessary transaction data to buy a specific NFT (execute_buy) or accept a pending offer (execute_sell).
Ask an AI about this
Waiting for input…
What AI agents can do with Reservoir (NFT Liquidity API) - 8 Tools
Use these eight tools to pull cross-platform NFT market data, check token metadata, or prepare trade execution payloads.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Reservoir (NFT Liquidity API) on VinkiusExecute Buy
Generates the required transaction payload needed to buy an NFT.
Execute Sell
Creates a transaction payload to accept a pending offer (fill a bid).
Get Collection
Fetches metadata and real-time stats for an entire NFT collection.
Get Token
Retrieves detailed information, including rarity, for a single specific token.
List Asks
Pulls all active sell listings (asks) from supported marketplaces in one query.
List Bids
Retrieves all active buy offers (bids) for tokens or entire collections.
List Tokens
Gets a list of tokens based on various filters, like owner address or collection contract.
Search Collections
Searches for NFT collections using either the name or the contract address.
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token
from cloud.vinkius.com. For OAuth-protected servers, expand
Advanced settings to add credentials.
Start a conversation
Open a new chat. The Reservoir integration is available immediately — no restart needed.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Reservoir (NFT Liquidity API), then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Built on the Model Context Protocol (MCP) for Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 8 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Checking NFT prices used to be a nightmare of tabs and copy/paste., Solved with Vinkius AI Gateway
If you're doing manual research, you open OpenSea. You check the floor price. Then you switch to LooksRare because they might have better deals. Next, you pivot to X2Y2 for volume comparison. This process involves logging into three different sites, finding the same collection by contract ID each time, and manually comparing the best bid versus ask across all of them.
With Reservoir, your agent runs `list_asks` once. It aggregates that data from every major marketplace you need to check. You get a single, structured output containing all active listings—no tab switching required.
Reservoir (NFT Liquidity API) MCP Server: Instant Market Data
You no longer have to manually search for collections by name, then find the contract address on a separate site, and finally input that into your analysis tool. The `search_collections` tool handles the lookup first.
The process is clean: ask your agent to identify the collection (`search_collections`), get its current stats (`get_collection`), and immediately see who owns it or what's for sale (`list_tokens`). It’s all one continuous, data-driven query.
What your AI can actually do with this
Reservoir NFT Liquidity API gives your AI agent direct, real-time access to NFT market data across major marketplaces like OpenSea, LooksRare, and X2Y2. It aggregates bids and asks, token metadata, and collection stats into a single stream for actioning trades or analysis. You connect this server, and your agent gets the tools it needs to operate on live market liquidity.
When you're checking cross-market listings, you can pull every active sell listing (asks) across supported platforms using list_asks, and retrieve all currently active buy offers (bids) for entire collections or specific tokens via list_bids. This means your agent doesn't have to check multiple sites; it gets both sides of the ledger in one query.
You can also use list_tokens to get a list of assets owned by an address, letting you filter those results based on criteria like rarity or contract type.
For deep market analysis, get_collection pulls real-time stats for any given NFT collection. That includes the floor price, total volume traded, and comprehensive metadata for the whole set. If your agent needs to dive into a single asset, get_token retrieves detailed information on that specific token, including its rarity score and history.
To find new opportunities or assets, you can use search_collections, which lets your agent look up collections either by name or using their contract address. You'll always have the ability to list tokens held by an owner with filters applied, giving you a clear picture of an entire portfolio.
When it comes time to execute trades, the API provides the transaction mechanism. If your agent needs to buy an NFT, execute_buy generates the exact transaction payload required for that purchase. Conversely, if there's a pending offer—a bid waiting to be accepted—your agent can use execute_sell to create the necessary transaction payload to fill that bid and complete the sale.
019e5d4f-f0f3-731c-a069-c899831c93b6 
Here's how it actually works
The bottom line is: it lets your agent treat multiple, disparate NFT marketplaces as if they were one single API endpoint.
Subscribe to this server and input your Reservoir API Key.
Your AI client calls one of the 8 available tools (e.g., get_collection for metadata).
The server returns structured, aggregated market data or transaction payload that your agent can use immediately.
Who is this actually for?
Web3 developers building trading bots need this. Quant analysts require a centralized data source to track market movements without scraping ten different sites. NFT traders use it when they need to compare liquidity depth across major marketplaces instantly.
Uses list_asks and get_collection to build algorithms that identify arbitrage opportunities by comparing price differences between different NFT collections or chains.
Runs search_collections and then uses list_bids and list_asks to determine the true market value of a token across three major platforms before making a purchase decision.
Calls get_token or list_tokens with specific filters (like owner address) to pull ownership data and rarity statistics for reporting purposes.
What Changes When You Connect
Stop checking OpenSea, LooksRare, and X2Y2 separately. Using list_asks or list_bids pulls active listings from multiple sources at once, giving you a single view of market depth.
Need to know if an NFT is rare? Call get_token with the contract address; it returns deep metadata and rarity scores instantly, saving manual lookup time.
Don't just analyze—act. The server generates transaction data using execute_buy, letting your agent prepare a purchase without leaving the chat window.
Research ownership patterns easily. Use list_tokens to pull all assets owned by a specific address and filter them, making it simple for due diligence.
Get collection health metrics with get_collection. You immediately see the floor price and 24h volume, allowing you to vet an asset before writing any code.
See it in action
Spotting Arbitrage Opportunities
A quant developer notices a collection's floor price is low on one site but high on another. They ask their agent to run list_asks across both platforms, identify the cheapest listing, and use execute_buy to prepare a cross-platform trade.
Due Diligence on an Opponent's Wallet
An analyst wants to see everything a competitor owns. They run list_tokens against the opponent's address, filtered by contract type. This immediately surfaces all their holdings and allows them to use get_collection on any asset found.
Automating Bid Monitoring
A trader needs to track a specific high-value token. They set up an agent that constantly runs list_bids for the target contract, alerting them when a bid reaches a certain threshold, so they can prepare to accept it with execute_sell.
Quick Collection Vetting
A user finds a new collection by name. Instead of visiting the site, they ask their agent to run search_collections, then use get_collection on the resulting contract ID. They get the floor price and volume in seconds.
The honest tradeoffs
Checking only one marketplace
The user manually checks OpenSea for a listing, assuming that's the best current price and ignores bids on LooksRare.
Always run list_asks first. This pulls active listings from all supported marketplaces at once, ensuring you see every available sale.
Treating metadata as static
Assuming a token's rarity score is constant and forgetting that the market price changes daily.
Use get_token to check core stats, but always cross-reference those findings with real-time data from list_asks or list_bids before making any trade decision.
Forgetting the transaction step
Getting all the data and concluding 'I should buy it' without knowing how to actually execute the purchase.
After deciding on a target, ask your agent to run execute_buy first. It gives you the exact transaction payload needed for the wallet.
When It Fits, When It Doesn't
Use this server if your workflow requires cross-platform data aggregation (i.e., comparing prices across multiple major marketplaces) or if you need to generate verifiable, actionable trade payloads. The core strength is combining listing data (list_asks, list_bids) with metadata (get_collection). Don't use it if you only need basic blockchain status checks or simple ERC-20 token lookups; those might be handled by a more general node service. If your goal is to build an automated trading bot, this server provides the necessary inputs—from list_asks all the way through to generating the trade execution via execute_buy. However, note that it does not predict future market movement or guarantee asset value; it only reports current, verifiable data points.
Questions you might have
How does the Reservoir (NFT Liquidity API) handle multiple marketplaces? +
The server aggregates data from major platforms like OpenSea and LooksRare. When you run list_asks, for example, it pulls all active listings from those sites into a single result set.
Can I use the Reservoir (NFT Liquidity API) to buy an NFT? +
Yes. After analyzing the data with tools like list_asks, you can generate the necessary transaction details using the execute_buy tool, preparing your agent for a trade.
What is the difference between `get_collection` and `search_collections`? +
search_collections finds the collection's contract ID based on a name or address. get_collection, however, uses that confirmed ID to pull real-time stats like floor price and volume.
Is this API just for viewing data? +
No. While it excels at reading market data (list_bids), the server also provides write capabilities through execute_sell to generate transaction payloads for accepting offers.
How do I authenticate when using list_asks? +
You include your API key in the request header. The server validates this credential before processing any query, guaranteeing that only authorized agents access live market data.
What are the rate limits when calling get_token? +
The service enforces standard rate limits to protect against overuse. We advise your agent client to implement exponential backoff logic for stable and reliable data retrieval over time.
How can I use list_tokens to filter by specific attributes? +
You pass the required criteria, like owner addresses or rarity scores, in the tool's parameters. This narrows your results set before it even hits the network, giving you highly targeted data.
What does execute_buy return if the NFT is already sold? +
The tool returns a specific error code and an explanatory message detailing why the transaction failed. This allows your agent to handle exceptions gracefully without crashing the workflow.
Can I check the floor price and volume for a specific NFT collection? +
Yes. Use the get_collection tool with the collection ID or contract address. It returns real-time stats including floor price, market cap, and volume metrics.
How do I see all active buy offers for a particular NFT? +
Simply use the list_bids tool and provide the token identifier (contract:tokenId). The agent will list all active offers across supported marketplaces.
Does this server allow me to actually buy an NFT through the AI? +
The execute_buy tool generates the necessary transaction data. You will still need to sign the transaction with your wallet (like MetaMask) to complete the purchase, ensuring full security.
We've already built the connector for Reservoir. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 8 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.