How to Use the Grain MCP in Vercel AI SDK

Q: How do I handle Grain authentication in Vercel AI SDK?

Use the authProvider option when initializing the MCP client on Vercel. This lets you securely pass OAuth tokens from your database so the Vercel AI SDK agent can safely call Grain tools via the MCP Server on behalf of individual users.

Q: Can I stream Grain transcripts in real-time with Vercel AI SDK?

Yes, by passing the gettranscript tool directly to streamText. The Vercel AI SDK handles the chunked response from the MCP Server, letting your UI display the meeting transcript text as it arrives.

Feed real-time Grain transcript and meeting data directly into your Vercel AI SDK frontend via our MCP Server without loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Grain MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Grain transcripts to Vercel AI SDK frontends

The `get_transcript` tool lets your Vercel AI SDK application pull complete, timestamped meeting logs with speaker names and stream them straight to your React or Next.js UI. Instead of making users wait for a massive text block to load, your interface renders the conversation line-by-line as the AI processes it. You set up the MCP client using `createMCPClient` in your Edge Functions, allowing the AI to fetch transcripts instantly when a user asks about a specific meeting. This setup bypasses heavy server-side processing and keeps your frontend completely interactive.

Render live meeting insights inside your UI

The `get_insights` tool extracts key takeaways from any call, allowing your Vercel AI SDK components to display structured summaries instantly. This means your users can view high-level decision points side-by-side with the streaming chat interface. By feeding the tool output directly into `streamText`, you avoid writing complex parsing logic. The AI handles the interpretation, and Vercel's UI primitives render the output as it arrives, keeping the user experience fast.

Trigger video uploads using Edge Functions

The `upload_video` tool lets you send external video URLs straight into Grain's processing pipeline directly from your Vercel AI SDK endpoint. Your frontend can accept a raw URL from an input field, pass it to the agent, and show the ingestion progress in real-time. Using the MCP Server tool-calling loop, the agent monitors the upload status and updates the UI state without full page reloads. This approach lets you build lightweight, serverless video intelligence tools that scale on Vercel's edge network.

Setup guide

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

Use the `authProvider` option when initializing the MCP client on Vercel. This lets you securely pass OAuth tokens from your database so the Vercel AI SDK agent can safely call Grain tools via the MCP Server on behalf of individual users.

Yes, by passing the `get_transcript` tool directly to `streamText`. The Vercel AI SDK handles the chunked response from the MCP Server, letting your UI display the meeting transcript text as it arrives.

Since Vercel AI SDK runs on Edge Functions with execution limits, you should set a strict timeout on your HTTP transport. If `list_recordings` takes too long, the edge function will catch the error and allow your UI to gracefully prompt the user to retry.

You filter the tools returned by the MCP Server before passing them to the SDK. If you only want your agent to read data, simply omit `upload_video` from the tool array passed to your model.

All audio, transcripts, and speaker identities remain securely on Grain's servers and are only fetched via encrypted HTTPS calls. The Vercel AI SDK acts as a temporary pass-through, meaning no meeting data is stored or cached on Vercel's edge nodes.

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