How to Use the Exa AI MCP in Vercel AI SDK

Q: Can I use Exa AI to find similar pages inside my Vercel AI SDK app?

Yes. Just pass a target URL to the findsimilar tool within your agent's tool set. It returns a list of related sites you can immediately display to your users.

Stream semantic web data directly into your Vercel AI SDK interface for real-time, live discovery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Exa AI MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Direct semantic search streaming

Feed your UI with live search data by piping `search_web` results into your streaming response. Your users see the information arrive as it happens, rather than waiting for a backend process to finish. This keeps your React or Next.js frontends responsive. By using `search_with_contents`, you skip the extra round trips and pull the exact context you need for your generation.

Targeted content retrieval

Grab clean text from specific URLs using `get_contents` to keep your context window focused. It strips out the junk so your agents only process relevant information. Since this MCP Server works with Edge Functions, you keep your latency low. It is the fastest way to get high-fidelity data into your streaming pipelines.

Usage tracking and limits

Monitor your bandwidth and crawl statistics with `get_api_usage` right from your application logic. You get immediate visibility into your search costs. Check these metrics before firing off a heavy `find_similar` query. It ensures your app stays within budget while maintaining high performance.

Setup guide

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

Connect the server via the MCP transport and pass the tools into your `streamText` function. Once registered, your agent can call `search_web` during the generation cycle.

Yes. Just pass a target URL to the `find_similar` tool within your agent's tool set. It returns a list of related sites you can immediately display to your users.

It does. The MCP integration is built to handle the lightweight requirements of edge environments, ensuring your searches don't bloat your runtime.

Your queries and the resulting web content are transient. They exist only in your agent's memory during the session and are not stored by the server.

Use standard TypeScript try-catch blocks around your tool execution. If a search fails, you can catch the error and prompt your agent to try a different query.

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