How to Use the FileStack MCP in Vercel AI SDK

Q: How do I configure FileStack with the Vercel AI SDK?

Install the @ai-sdk/mcp package and connect to the MCP Server using createMCPClient. Pass the tools directly into generateText or streamText to let your agent call FileStack actions.

Q: How does the Vercel AI SDK handle FileStack video transcoding delays?

Your agent initiates the transcode using startvideotranscode and handles the waiting period asynchronously. It polls getvideostatus while streaming progress updates back to the UI, ensuring the browser remains responsive.

Q: Do I need to close the connection after running a file transformation?

Yes, you must always call mcpClient.close() when your execution finishes. This prevents connection leaks in serverless environments like Vercel.

Pipe live FileStack media transformations and OCR extraction directly into your Next.js frontend using 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 FileStack MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time OCR streaming with Vercel AI SDK

The `get_ocr` tool extracts printed or handwritten text from documents and feeds it directly into your frontend stream. When your user uploads a receipt or invoice, this MCP Server processes the file and lets the Vercel AI SDK render the extracted text line-by-line in your UI. This setup cuts out the typical loading spinner and keeps the interface responsive. By passing the tool output to `streamText`, your application parses document data without blocking the main thread. You get a fast, event-driven pipeline where users see text extraction happen in real-time.

Instant image processing inside Edge Functions

The `generate_transform_url` tool builds CDN transformation URLs instantly without executing heavy image processing on your server. Your Next.js edge route calls this tool to generate resized or cropped image paths, which the Vercel AI SDK then passes to your frontend components. This keeps your edge runtime lightweight and fast. Combine this with `get_image_tags` to analyze image content and update your UI state dynamically. The agent inspects the asset, generates a new visual variant, and pushes the updated image URL to the client in a single fluid motion.

Asynchronous video transcoding in streaming chat

The `start_video_transcode` tool initiates video conversion and returns a tracking ID for your streaming interface. Because video processing takes time, this MCP Server lets your Vercel AI SDK agent start the job and then poll `get_video_status` to update the user on progress. Your UI shows a live progress bar as the agent repeatedly checks the status. Once transcoding finishes, the agent automatically displays the final video player in the chat window.

Setup guide

Set up FileStack 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 FileStack 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 FileStack 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 Filestack. 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 FileStack 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 FileStack MCP in Vercel AI SDK

Install the `@ai-sdk/mcp` package and connect to the MCP Server using `createMCPClient`. Pass the tools directly into `generateText` or `streamText` to let your agent call FileStack actions.

Yes, because this MCP Server runs on Vinkius, your edge functions only make lightweight HTTP calls. You can trigger `get_image_tags` or `get_sfw_status` from Vercel Edge Functions without running into bundle size or execution limit issues.

Your agent initiates the transcode using `start_video_transcode` and handles the waiting period asynchronously. It polls `get_video_status` while streaming progress updates back to the UI, ensuring the browser remains responsive.

Yes, you must always call `mcpClient.close()` when your execution finishes. This prevents connection leaks in serverless environments like Vercel.

Your raw files, images, and videos are processed in isolated V8 sandboxes on Vinkius. Temporary files are wiped immediately, and the server never stores your OCR text or media metadata after the request completes.

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