How to Use the Jina AI (Search Foundation & LLM Grounding) MCP in Vercel AI SDK

Feed clean web data directly into your Next.js UI using Vercel AI SDK and this search-focused MCP server.

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 (Search Foundation & LLM Grounding) MCP to Vercel AI SDK

Create your Vinkius account to connect Jina AI (Search Foundation & LLM Grounding) 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 (Search Foundation & LLM Grounding) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time search streaming with Vercel AI SDK

The `search_web_jina` tool queries the live web to return structured, context-rich search results directly to your application. By hooking this into your Vercel AI SDK setup, you bypass the typical slow backend wait times. Your users watch search results stream onto the screen in real-time as the model processes them. This setup runs directly in Edge Functions without cold start penalties. You get clean JSON payloads that map straight to your React components, letting you build search interfaces that feel instant.

Clean web scraping for UI grounding

The `read_url_content` tool extracts clean, markdown-formatted text from any URL to ground your LLM responses. When a user drops a link into your Vercel AI SDK chat interface, this tool strips the junk, ads, and navigation menus immediately. The model receives only the core content, which keeps your token usage low and speeds up response times. Your chat interface displays the source content cleanly alongside the generated answer without needing custom scraping scripts.

Smart chunking and reranking at the edge

The `segment_content` and `rerank_documents` tools split long documents into semantic chunks and score them against the user's query. This prevents your Vercel AI SDK context window from overflowing when handling massive articles or PDFs. Your application only streams the highly relevant chunks back to the user interface. This reduces latency on mobile connections and guarantees that the generated UI components display highly accurate source citations.

Setup guide

Set up Jina AI (Search Foundation & LLM Grounding) 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 (Search Foundation & LLM Grounding) 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 (Search Foundation & LLM Grounding) 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 (Search Foundation & LLM Grounding) 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 (Search Foundation & LLM Grounding) MCP in Vercel AI SDK

You configure standard backoff logic in your Next.js route handlers. Since the Vercel AI SDK handles streaming chunks, you should catch API limits before initiating the stream. Vinkius manages the underlying MCP server connection to keep your API keys secure.

Yes, the server runs on Vinkius, which means your Edge Functions only need to make standard HTTP calls. You initialize the MCP client in your route, execute tools like `search_web_jina`, and stream the output to the client. This keeps your edge deployment lightweight and fast.

It provides direct access to semantic search and clean web scraping without requiring a heavy backend infrastructure. By calling `rerank_documents` directly from your Vercel AI SDK code, you ensure the LLM gets the most relevant context. This leads to faster generation times and more accurate UI rendering.

You call the tools method on your initialized client and pass the resulting object to the tools parameter of streamText. The Vercel AI SDK automatically handles the execution of tools like `classify_texts` during the generation cycle. Remember to call close on your client when the stream finishes.

Your raw text chunks, URLs, and search queries are processed securely through the Vinkius MCP server sandbox before reaching the endpoints. No data is stored or used for training purposes. The connection uses ephemeral tokens to ensure your users' private search queries remain confidential.

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