How to Use the Jina AI MCP in Vercel AI SDK

Q: How do I stream search results from Jina AI using Vercel AI SDK?

You initialize the client using createMCPClient and pass the tools directly to streamText. When the agent decides to search, the searchweb tool fires, and the results flow into your Vercel AI SDK UI chunk by chunk.

Pipe Jina AI search results and clean web content directly into your UI 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 Jina AI MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live search streaming in Vercel AI SDK

When your user asks a question, your Vercel AI SDK app shouldn't freeze behind a loading spinner. By hooking `search_web` to your Vercel AI SDK setup, you feed raw Jina AI search results directly into the UI stream as they land. The Vercel AI SDK client handles the incoming Jina search chunks instantly. Your user watches the agent find sources via `search_web`, pull clean markdown with `read_url`, and draft the final answer in real-time.

Clean up web noise before your model reads it

Sending raw HTML to an LLM wastes tokens and blows up your Vercel serverless bill. This Jina AI MCP Server strips out ads, scripts, and navigation menus before the Vercel AI SDK processes the payload. Your Vercel AI SDK agent calls `read_url` to get clean markdown, then uses `tokenize_text` to verify the exact payload size before running generation. It keeps your Vercel edge functions fast and your token usage predictable.

Rerank search results on the fly

Standard search APIs return too much junk, which confuses your Vercel AI SDK model. With Vercel AI SDK, you can pipe those Jina AI search results straight into `rerank_documents` to sort them by actual relevance to the user's prompt. This means your Vercel AI SDK UI only displays the most relevant Jina AI search context. You can also run `check_fact` on the top results to verify claims before rendering them to the screen.

Setup guide

Set up Jina 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 Jina 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 Jina 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 Jina 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 Jina 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 Jina AI MCP in Vercel AI SDK

You initialize the client using `createMCPClient` and pass the tools directly to `streamText`. When the agent decides to search, the `search_web` tool fires, and the results flow into your Vercel AI SDK UI chunk by chunk.

Yes. Because Vinkius hosts the MCP Server on a secure endpoint, your Vercel AI SDK edge runtime doesn't need to spin up heavy local processes. Just connect via HTTP transport and start reading clean markdown with `read_url`.

Instead of feeding ten raw search pages to your LLM, you use `rerank_documents` to select the top three. This cuts down the token payload size dramatically before Vercel AI SDK calls your model.

Call the MCP client tools to get the schema definitions, then spread them into the tools parameter of `generateText`. Remember to call `mcpClient.close()` once the request finishes to prevent connection leaks.

Every URL you read and search query you send goes through Vinkius's ephemeral V8 sandbox hosting the MCP server. Jina AI processes the text chunks to strip noise, but your data is never stored or used for training.

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