How to Use the Glean MCP in Vercel AI SDK

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

You initialize the client using createMCPClient over HTTP and pass the tools directly to streamText. The searchdocs tool will then pipe document snippets directly to your React components as they arrive.

Q: Can I use Glean autocomplete features in Vercel AI SDK inputs?

Yes, you can hook the autocomplete tool into your search input components. The Vercel AI SDK calls this endpoint to fetch trace logs and vault limits in real-time, updating the UI dropdown as the user types.

Q: How do I clear document indexes using this setup?

You call the deletedocument tool within your Vercel AI SDK server actions. This triggers the Glean system to clean up internal arrays and remove the specified document from your search index.

Stream enterprise search results directly into your React components in real-time using Glean and the 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 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 Glean search results to your Vercel AI SDK UI

The `search_docs` tool lets your AI client find internal documents within the Headless Glean Platform and stream them instantly. Instead of waiting for a massive payload to load behind a spinner, this integration pipes individual CRM records and documentation snippets directly to your frontend as they resolve. We construct this using `createMCPClient` to establish an edge-compatible link. This means your Next.js edge functions call the Glean MCP Server, fetch the required files, and feed them straight into `streamText` for zero-latency UI rendering.

Feed real-time AI answers into your chat interface

The `get_answer` tool fetches structured rules and active billing information directly from Glean to resolve complex user queries. When a user asks a question, the Vercel AI SDK processes the request and calls this tool to retrieve precise, verified answers without making the user wait. By passing the MCP client tools directly into your `generateText` system, you bypass custom API glue code. Your chat components render the resulting data stream instantly, keeping the conversational interface fast and responsive.

Index custom developer docs on the fly

The `index_document` tool allows your application to insert custom documentation payloads directly into the Glean index via native gateway authentication. This means when a developer uploads a new markdown file or PDF through your Vercel AI SDK app, the background process indexes it immediately. You handle this securely by configuring the `authProvider` during the MCP client setup. The server processes the document, handles the auth, and updates your enterprise search index so the very next search query can find it.

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 initialize the client using `createMCPClient` over HTTP and pass the tools directly to `streamText`. The `search_docs` tool will then pipe document snippets directly to your React components as they arrive.

Yes, you can hook the `autocomplete` tool into your search input components. The Vercel AI SDK calls this endpoint to fetch trace logs and vault limits in real-time, updating the UI dropdown as the user types.

Yes, this MCP Server works in edge runtimes when connected via Vercel AI SDK. It communicates over standard HTTP transport, avoiding Node-specific APIs so you can run search queries right from the edge.

You call the `delete_document` tool within your Vercel AI SDK server actions. This triggers the Glean system to clean up internal arrays and remove the specified document from your search index.

All search queries and SaaS document metadata are processed inside an ephemeral V8 sandbox on Vinkius. Your Vercel AI SDK client connects using a single secure token, meaning your raw enterprise data never persists on our servers.

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