How to Use the Glean MCP in Vercel AI SDK

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

You call mcpClient.tools() and pass them directly into streamText. The SDK handles the tool execution automatically when your user asks a question, streaming the matches from search into your UI.

Q: Can I use Vercel AI SDK to filter Glean results by app?

Yes, you can. You run searchbydatasource through the SDK to restrict search queries to specific platforms like Slack or Google Drive. This prevents cluttering your UI with irrelevant results.

Q: Does Vercel AI SDK support secure OAuth with Glean?

Yes. You configure an authProvider during the createMCPClient setup. This ensures that every streamed search query respects the user's specific access permissions defined in your corporate workspace.

Q: What is the best way to verify the connection status?

You run checkgleanstatus during your application's initialization sequence. If the status check fails, you can gracefully fall back to a cached state or display a helpful message in your UI.

Build Next.js apps that stream real-time workspace answers to your users via Vercel AI SDK and Glean.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Glean MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream workspace search results directly to your React UI

This capability relies on `search` to feed your Next.js application with instant company-wide search results. Instead of waiting for a complete JSON response from multiple integrations, Vercel AI SDK streams chunks of document titles and matches directly into your custom components. Users get immediate visual feedback as soon as the first byte of data is returned. This approach cuts down perceived latency by over 40% compared to traditional loading spinners.

Vercel AI SDK fetches and renders specific wiki entries

This feature uses `get_document` to pull exact file details into your Edge Functions on demand. When an employee clicks a streamed search result, Vercel AI SDK calls this MCP tool to render the file contents inline without a full page reload. You configure this node to run on the edge for fast startup times. It keeps your interface snappy because it avoids heavy server-side rendering steps.

Run instant member lookups in your input fields

This setup runs `autocomplete` to predict what users are typing in your search bar. Your Vercel AI SDK frontend triggers this tool on every keystroke, fetching matching workspace tags and documents instantly. By connecting this MCP Server to your input components, you bypass the need to build a custom autocomplete engine. The server handles the heavy matching logic, and your UI just renders the array.

Setup guide

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

You call `mcpClient.tools()` and pass them directly into `streamText`. The SDK handles the tool execution automatically when your user asks a question, streaming the matches from `search` into your UI.

Yes, you can. You run `search_by_datasource` through the SDK to restrict search queries to specific platforms like Slack or Google Drive. This prevents cluttering your UI with irrelevant results.

Yes. You configure an `authProvider` during the `createMCPClient` setup. This ensures that every streamed search query respects the user's specific access permissions defined in your corporate workspace.

You run `check_glean_status` during your application's initialization sequence. If the status check fails, you can gracefully fall back to a cached state or display a helpful message in your UI.

All crawled wiki entries, employee profiles, and Slack messages remain inside your secure Glean environment. This MCP Server runs in a sandboxed V8 Isolate, meaning your raw corporate files are never stored or exposed to external networks.

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