How to Use the Helius (Solana) MCP in Vercel AI SDK

Q: How do I configure Helius (Solana) with Vercel AI SDK?

Install the @ai-sdk/mcp package and initialize the client using the Vinkius HTTP endpoint. Pass the tools returned by mcpClient.tools() directly into the tools parameter of generateText or streamText. Remember to call mcpClient.close() once your execution finishes to prevent memory leaks.

Q: How do I handle priority fees before sending a transaction?

Call getpriorityfeeestimate through your agent to get the current optimal fee rates. This tool provides accurate gas pricing based on recent blocks, which your frontend can immediately display to prevent transaction drops.

Get live Solana asset data and priority fees in your React frontend using the Helius (Solana) MCP Server on 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 Helius (Solana) MCP to Vercel AI SDK

Create your Vinkius account to connect Helius (Solana) 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 Helius (Solana) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time asset tracking in your UI

Tracking wallet assets relies on the `get_assets_by_owner` and `get_wallet_balances` tools to pull live balances. When your user queries an address, this MCP Server lets Vercel AI SDK stream the owner's token balances and NFT metadata straight to their screen. You can also feed `search_assets` results directly into your streaming UI components. The agent parses the parameters, hits the Helius indexer, and outputs the exact compressed NFTs or tokens your user asked for without freezing the main thread.

Instant transaction parsing and history

Decoding on-chain events uses `parse_transactions` and `get_transaction_history` to build readable feeds. Your interface displays human-readable transaction histories by feeding raw data into the parser, letting your frontend agent format it dynamically inside your Next.js or React components. When a user asks for their financial history, the agent pulls past activity. Because Vercel AI SDK handles edge execution, this data reaches the user's browser in milliseconds, keeping the entire experience snappy.

Dynamic fee estimates for fast transactions

Managing transaction execution requires `get_priority_fee_estimate` and `get_token_accounts` to prevent dropped transactions. This MCP Server provides your agent with live network rates, ensuring users don't get stuck waiting for a block that will never confirm. By verifying user holdings, your application can estimate the exact fee required for a successful transfer. It makes the entire execution path transparent and reliable for end users.

Setup guide

Set up Helius (Solana) 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 Helius (Solana) 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 Helius (Solana) 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 Helius. 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 Helius (Solana) 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 Helius (Solana) MCP in Vercel AI SDK

Install the `@ai-sdk/mcp` package and initialize the client using the Vinkius HTTP endpoint. Pass the tools returned by `mcpClient.tools()` directly into the `tools` parameter of `generateText` or `streamText`. Remember to call `mcpClient.close()` once your execution finishes to prevent memory leaks.

Yes, you can stream live token details directly into your frontend. By calling `get_wallet_balances` through the SDK's streaming text or UI functions, the agent retrieves USD values and token balances, rendering them incrementally as they arrive from the Helius indexer.

Yes, the server runs smoothly in edge environments. Since Vinkius hosts the actual MCP Server, your edge function only needs to make a lightweight HTTP call to trigger tools like `get_asset` or `get_wallet_identity`.

Call `get_priority_fee_estimate` through your agent to get the current optimal fee rates. This tool provides accurate gas pricing based on recent blocks, which your frontend can immediately display to prevent transaction drops.

Your wallet addresses and token balances are safe because Vinkius runs in a zero-trust, ephemeral sandbox. The server only queries public ledger records and never touches private keys, ensuring your financial secrets remain isolated.

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