How to Use the Kava Explorer MCP in Vercel AI SDK

Q: How do I connect Kava Explorer to Vercel AI SDK?

Install @ai-sdk/mcp and instantiate it using createMCPClient. Point the HTTP transport URL to your Vinkius endpoint. Then pass the resulting tools to your streamText function.

Q: Does this support real-time block tracking?

Yes, calling getblock fetches the latest chain height. Your agent polls this tool to update the UI as new blocks finalize.

Q: How do I handle large transaction lists in Vercel AI SDK with Kava Explorer?

Pass pagination arguments to listextrinsics. The SDK streams the filtered results back to your frontend in chunks, keeping the UI responsive.

Build live Kava blockchain explorers in React with Vercel AI SDK. Stream real-time blocks and account balances straight to the UI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kava Explorer MCP to Vercel AI SDK

Create your Vinkius account to connect Kava Explorer 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 Kava Explorer with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Kava Account Data to React

The Kava Explorer MCP Server exposes `get_account_info` and `get_account_token` to pull live wallet balances. Vercel AI SDK pipes this data straight into your Next.js frontend as the agent fetches it. Users watch their token holdings appear on screen without waiting for a loading spinner. Writing custom Subscan API wrappers wastes time. Pass the MCP client to `streamText`, and your AI client handles the REST calls natively. It grabs the exact account state and renders it into your UI components instantly.

Build Live Transaction Monitors

Your agent uses `get_extrinsic` and `list_extrinsics` to track specific on-chain actions. When a user asks about a failed transaction, the model reads the chain state and streams the explanation back. This turns a complex block explorer into a simple chat interface. Edge functions handle the heavy lifting. The SDK connects to the MCP Server over HTTP, queries the Subscan backend, and returns the extrinsic details. You get typed, parseable responses ready for your Svelte or Vue application.

Render Validator Metrics On Demand

Querying `list_validators` and `get_validator` gives you the current staking metrics on Kava. Vercel AI SDK takes these raw JSON payloads and feeds them to your generative UI. Your application instantly displays a chart of top validators based on user prompts. Staking rewards require precise tracking. Calling `get_account_reward_slash` pulls the exact history of a delegator's earnings. The agent streams this historical data into a clean, readable format directly inside the user's dashboard.

Setup guide

Set up Kava Explorer 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 Kava Explorer 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 Kava Explorer 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 Kava Explorer. 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 Kava Explorer 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 Kava Explorer MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and instantiate it using `createMCPClient`. Point the HTTP transport URL to your Vinkius endpoint. Then pass the resulting tools to your `streamText` function.

Yes, calling `get_block` fetches the latest chain height. Your agent polls this tool to update the UI as new blocks finalize.

The HTTP transport works natively on Edge runtimes. Deploy your Next.js app globally and query the Kava chain with minimal latency.

Pass pagination arguments to `list_extrinsics`. The SDK streams the filtered results back to your frontend in chunks, keeping the UI responsive.

This MCP Server reads public Kava blockchain data like wallet addresses, token balances, and validator metrics. It never requests private keys or signs transactions. Security relies on standard HTTPS encryption between your application and the Vinkius endpoint.

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