How to Use the GeckoTerminal (DeFi Token Tracker) MCP in Vercel AI SDK

Q: Can the Vercel AI SDK stream GeckoTerminal (DeFi Token Tracker) data?

Yes. When the agent calls listtoppoolsnetwork, the framework streams the raw JSON chunks to your frontend. You can render the pool data as it arrives instead of waiting for the full response.

Stream live DeFi token and liquidity pool data straight to your frontend with the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GeckoTerminal (DeFi Token Tracker) MCP to Vercel AI SDK

Create your Vinkius account to connect GeckoTerminal (DeFi Token Tracker) 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 GeckoTerminal (DeFi Token Tracker) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Live Charts via MCP Server

Your users don't want to stare at loading spinners while fetching market data. Connect this MCP server to your Vercel AI SDK app and stream `get_ohlcv` results straight into a React charting component. The agent fetches historical price data and renders the candles live. You can do the same for recent transactions. Hook up `list_trades` to a streaming table. As the LLM pulls the latest swaps for a specific pool, the rows appear in the UI instantly. It feels fast because the data pipes directly from GeckoTerminal to the client edge.

Build Real-Time Discovery Dashboards

DeFi moves quick. You need to show what's happening right now across 100+ blockchains. Use `get_trending_pools_all` to pull the hottest liquidity pools globally, then map the data into a Svelte or Vue grid. If your users care about a specific chain, narrow it down. Call `get_trending_pools_network` or `get_new_pools_network`. Your agent grabs the raw JSON, formats the pool addresses and volume metrics, and streams the finished components to the browser.

Inject Deep Token Metrics into Next.js

Sometimes a user asks about a specific asset. When they type a contract address into your chat interface, the agent triggers `get_token` and `get_token_info`. It pulls metadata, total supply, and current price. Then it digs deeper. It runs `list_top_pools_for_token` to find where the liquidity actually sits. By the time the AI finishes typing its response, your frontend has already rendered a complete market depth profile.

Setup guide

Set up GeckoTerminal (DeFi Token Tracker) 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 GeckoTerminal (DeFi Token Tracker) 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 GeckoTerminal (DeFi Token Tracker) 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 GeckoTerminal. 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 GeckoTerminal (DeFi Token Tracker) 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 GeckoTerminal (DeFi Token Tracker) MCP in Vercel AI SDK

Run npm install ai @ai-sdk/mcp in your project. Initialize it with createMCPClient using your Vinkius HTTP transport URL. Pass the resulting tools directly to streamText.

Yes. When the agent calls `list_top_pools_network`, the framework streams the raw JSON chunks to your frontend. You can render the pool data as it arrives instead of waiting for the full response.

It supports over 100 blockchains. You can check the exact list dynamically by having your agent run `list_networks` during the chat session.

Always call mcpClient.close() when your edge function finishes. Dangling connections will cause memory leaks in production environments.

It strictly reads public on-chain metrics like pool volumes, OHLCV charts, and DEX trades. Vinkius runs the server in an ephemeral V8 Isolate, meaning your request parameters vanish the second the HTTP transport closes.

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