How to Use the Haystack (deepset Cloud) MCP in Vercel AI SDK

Q: How do I query Haystack (deepset Cloud) documents in Vercel AI SDK?

You initialize the client, expose the searchdocuments tool, and pass it into the tools array of your streamText function. The SDK handles the transport, and the search results stream right into your response.

Connect Haystack (deepset Cloud) to Vercel AI SDK to stream live document search results and pipeline outputs directly into your React UI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Haystack (deepset Cloud) MCP to Vercel AI SDK

Create your Vinkius account to connect Haystack (deepset Cloud) 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 Haystack (deepset Cloud) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time document search streaming

Feed live document chunks from your index straight into your frontend components. Using `search_documents` with the Vercel AI SDK ensures your users see data flowing as the model processes it. Stop waiting for full page loads. This MCP Server pipes raw index data into your stream, letting you build interfaces that feel instant and responsive.

On-demand RAG pipeline execution

Trigger complex search logic from your edge functions using `run_pipeline`. Your AI client calls the server, and the results appear in your UI without extra backend routing. Keep your logic centralized in deepset Cloud while your frontend handles the display. It's clean, fast, and keeps your search state synchronized with your application state.

Manage workspaces and file metadata

Query your environment status directly from your code with `list_workspaces` and `list_files`. You can verify your connection state before firing off heavy search requests. Getting file metadata via `get_file` allows you to validate assets before rendering. It gives your application the context it needs to show the right information at the right time.

Setup guide

Set up Haystack (deepset Cloud) 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 Haystack (deepset Cloud) 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 Haystack (deepset Cloud) 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 deepset Cloud. 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 Haystack (deepset Cloud) 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 Haystack (deepset Cloud) MCP in Vercel AI SDK

You initialize the client, expose the `search_documents` tool, and pass it into the `tools` array of your `streamText` function. The SDK handles the transport, and the search results stream right into your response.

Yes. Since this MCP Server uses standard transport protocols, you can call it from edge functions. This keeps your search latency low and your Vercel AI SDK performance high.

You can implement logic in your route handlers to intercept tool calls before they run. This is standard in Vercel AI SDK, giving you full control over when `run_pipeline` executes.

Errors bubble up through the tool execution promise. You should wrap your calls in standard try-catch blocks to ensure your UI displays a fallback if a pipeline fails to return data.

It accesses your indexed document content, pipeline configurations, and workspace file metadata. It does not store your data; it only acts as a pass-through for your specific search queries.

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