How to Use the Nansen (Blockchain Analytics) MCP in Vercel AI SDK

Q: How do I start using Nansen (Blockchain Analytics) with the Vercel AI SDK?

Install the @ai-sdk/mcp package and use createMCPClient to point to your Vinkius endpoint. You pass the tools from mcpClient.tools() into the generateText or streamText functions. The SDK handles the rest.

Q: Can I filter which of the 48 Nansen tools my AI SDK app can access?

Yes. After you initialize the client with createMCPClient, the mcpClient.tools() method returns an object of all available tools. You can filter this object in your code before passing it to your AI model, giving you full control.

Stream Nansen's on-chain data directly into your Next.js app. With the Vercel AI SDK, you build interfaces that show analytics as they happen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nansen (Blockchain Analytics) MCP to Vercel AI SDK

Create your Vinkius account to connect Nansen (Blockchain Analytics) to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Nansen (Blockchain Analytics) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Live Wallet Profilers

Stop making users wait. When they enter a wallet address, you can use the Vercel AI SDK to stream Nansen data right into your UI components. The page builds itself in front of their eyes. Your app can instantly call `profiler_pnl_summary` to show aggregate profit, then populate a table with `profiler_transactions`, and finally draw a graph of `profiler_counterparties`. It’s a much better experience than a loading spinner.

Track Smart Money in Real-Time

Give your users a live view of what sophisticated traders are doing. You can build a dashboard that shows every transaction as it confirms on-chain, not five minutes later. Combine `smart_money_dex_trades` for the raw trade feed with `smart_money_netflow` to chart inflows and outflows. Since the AI SDK streams results, your UI updates with each new piece of data from the MCP server, creating a live market ticker.

Visualize Prediction Market Odds

Create frontends that react to changes in prediction markets. Your users can browse markets with `prediction_market_screener` and see the odds shift second by second. Once a market is selected, you can stream the order book using `prediction_orderbook` and chart price action with `prediction_ohlcv`. This lets you build highly reactive UIs for traders who need immediate information.

Setup guide

Set up Nansen (Blockchain Analytics) MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Nansen (Blockchain Analytics) tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Nansen (Blockchain Analytics) transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Nansen. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Nansen (Blockchain Analytics) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Nansen (Blockchain Analytics) MCP in Vercel AI SDK

Install the `@ai-sdk/mcp` package and use `createMCPClient` to point to your Vinkius endpoint. You pass the tools from `mcpClient.tools()` into the `generateText` or `streamText` functions. The SDK handles the rest.

Yes. After you initialize the client with `createMCPClient`, the `mcpClient.tools()` method returns an object of all available tools. You can filter this object in your code before passing it to your AI model, giving you full control.

A great starter project is a simple wallet dashboard. Create an input field for a wallet address and use `streamText` to display the output of `profiler_current_balance` and `profiler_pnl_summary`. It’s a quick way to see the streaming UI in action.

Yes. The server is designed for low-latency responses, and tools like `agent_fast` are specifically tuned for quick lookups. The Vercel AI SDK's streaming capabilities are built to handle this, rendering data as it arrives instead of waiting for the full response.

Your Nansen API keys are stored and managed by Vinkius, not in your frontend code. Your app communicates with the MCP Server, which processes on-chain data like wallet transactions and DeFi positions. The only data sent from your user's browser is the input, like a wallet address or token symbol.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript