How to Use the Covalent MCP in Vercel AI SDK

Q: How do I authenticate Covalent requests in Vercel AI SDK?

Pass your token using the authProvider configuration inside createMCPClient. This secures your calls to gettokenbalances on the server side so your client-facing React app never exposes raw API keys.

Q: Can Vercel AI SDK stream Covalent DEX pool data to edge functions?

Yes. You can import @ai-sdk/mcp and call getdexpools inside your Next.js Edge route. The tool results stream directly into streamText, keeping your serverless execution times under the strict edge limits.

Q: Does this Covalent MCP server support React Server Components in Vercel AI SDK?

Yes. You fetch the tools using mcpClient.tools() in your Server Action, pass them to the model, and stream the UI components back to the client. This keeps the Covalent MCP setup light because the parsing stays on the server.

Q: How do I close the connection after fetching wallet histories?

You must call mcpClient.close() once your stream finishes. This prevents active HTTP connections from hanging in your serverless environment after pulling data with gethistoricalportfolio.

Feed live multi-chain portfolio history and token balances directly into React components using 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 Covalent MCP to Vercel AI SDK

Create your Vinkius account to connect Covalent 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 Covalent with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Live Wallet Portfolios to React

The `get_historical_portfolio` tool lets your Vercel AI SDK app pull daily USD balances and historical price points for any wallet address instantly. Instead of making users wait for heavy backend processes, your Next.js UI streams this raw financial data straight into your React charts as the model processes it. You feed this tool directly into your Vercel AI SDK `streamText` function along with `get_token_balances` to show users their current on-chain holdings. Because Vercel AI SDK handles Edge Functions natively, your Covalent data queries remain fast and responsive without cold-start lag.

Real-time NFT and DEX Pool UI Updates

The `get_nft_balances` tool fetches contract names, token IDs, and image links directly to your Vercel AI SDK frontend without requiring a custom indexer. Your user-facing agent calls this alongside `get_dex_pools` to render liquidity pool metrics and NFT collections on the fly. By passing these tools into your Vercel AI SDK MCP setup, your client-side components render the actual images and pool reserves live. Users watch the AI populate their token dashboards step-by-step instead of staring at a blank loading screen.

Debug Transactions with this MCP Server

The `get_transaction_details` tool extracts raw log events, decoded parameters, and gas consumption metrics for any transaction hash. Your Vercel AI SDK chat interface displays these technical details in a clean, readable format as soon as the model parses them. Combining this with `get_token_transfers` allows your Vercel AI SDK application to build interactive block explorers inside a simple chat bubble. You just close the connection using `mcpClient.close()` when the stream finishes to keep your serverless execution clean.

Setup guide

Set up Covalent 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 Covalent 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 Covalent 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 Covalent. 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 Covalent 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 Covalent MCP in Vercel AI SDK

Pass your token using the `authProvider` configuration inside `createMCPClient`. This secures your calls to `get_token_balances` on the server side so your client-facing React app never exposes raw API keys.

Yes. You can import `@ai-sdk/mcp` and call `get_dex_pools` inside your Next.js Edge route. The tool results stream directly into `streamText`, keeping your serverless execution times under the strict edge limits.

Yes. You fetch the tools using `mcpClient.tools()` in your Server Action, pass them to the model, and stream the UI components back to the client. This keeps the Covalent MCP setup light because the parsing stays on the server.

You must call `mcpClient.close()` once your stream finishes. This prevents active HTTP connections from hanging in your serverless environment after pulling data with `get_historical_portfolio`.

The server only processes public wallet addresses and transaction hashes that you pass to tools like `get_transactions`. No private keys or seed phrases ever touch the Vinkius sandbox, keeping your users' on-chain credentials safe.

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