How to Use the GroundX MCP in Vercel AI SDK

Q: How do I perform a search in GroundX using the Vercel AI SDK?

You instantiate the MCP client and pass searchcontent into your tool array within the streamText function. Once invoked, the SDK manages the connection and streams the results straight to your frontend.

Q: Can I monitor ingestion status for GroundX within Vercel AI SDK?

Yes, you poll getingeststatus inside your agent logic. This confirms when your documents are indexed and ready for your AI client to query.

Q: Does this MCP server support local file ingestion?

You use ingestdocuments to push local paths or URLs directly into your storage. It works for both static files and remote web content.

Connect GroundX to your Vercel AI SDK project to stream live document search results directly into your React or Next.js UI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GroundX MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time RAG streams in AI SDK

Feed your UI live search results by piping `search_content` directly into your `streamText` calls. The Vercel AI SDK handles the message handshake so your users see data populate instantly instead of waiting on a static response. This bypasses the usual lag of backend processing. You just map the tool output to your frontend components and the data flows from GroundX to your users in one continuous stream.

Automated ingestion tracking

Keep your frontend synced with ingestion progress by calling `get_ingest_status` after you trigger an upload. This lets you show progress bars or loading states while `ingest_documents` processes your files in the background. Your application stays reactive to server-side state changes. You don't have to guess if a document is ready for search because your agent checks the status before the user ever attempts a query.

Dynamic bucket management

Organize your data architecture from within your application using `create_bucket` and `list_buckets`. This allows your AI client to dynamically partition user data or project files without manual database intervention. It keeps your data clean and segmented. You can spin up new containers for every session and clean them up using `list_content` to verify exactly what is being indexed at any given time.

Setup guide

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

You instantiate the MCP client and pass `search_content` into your tool array within the `streamText` function. Once invoked, the SDK manages the connection and streams the results straight to your frontend.

Yes, you poll `get_ingest_status` inside your agent logic. This confirms when your documents are indexed and ready for your AI client to query.

Your documents remain isolated within your specific bucket. We handle authentication through your endpoint token, ensuring the AI client only accesses the data you explicitly permit.

You use `ingest_documents` to push local paths or URLs directly into your storage. It works for both static files and remote web content.

The server performs semantic segmentation automatically upon ingestion. You simply search via `search_documents` and the engine returns the most relevant snippets for your AI client.

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