How to Use the Azure Blob Container MCP in Vercel AI SDK

Q: How do I use the Vercel AI SDK to list files in an Azure Blob Container?

Invoke streamText with a prompt like "list all text files." The Vercel AI SDK will call the listblobs tool from this MCP server and stream the file names back. You can feed this stream directly into a state variable to update your React or Svelte UI in real-time.

Q: Can I upload files to an Azure Blob Container with the Vercel AI SDK?

Yes. Your agent can use the putblob tool. Just give the AI the file content and a destination path, and the tool uploads it to your configured container. It's ideal for letting users save generated text or data.

Q: Is it possible to delete blobs from an Azure Blob Container using the Vercel AI SDK?

Absolutely. The deleteblob tool gives your agent the ability to remove files. Since this action is permanent, we recommend building a confirmation dialog in your UI before letting the agent proceed with the call.

Stream file contents from Azure Blob Storage directly into your UI components. The Vercel AI SDK makes your app feel instant.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Azure Blob Container MCP to Vercel AI SDK

Create your Vinkius account to connect Azure Blob Container 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 Azure Blob Container with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Read and Write Files Live

Let users interact with Azure Blob Storage without waiting for a loading spinner. Your agent can take a file, send it to the container with `put_blob`, and then immediately use `get_blob` to stream the contents back into a `<pre>` tag. It all happens in one continuous flow, right in the browser. This isn't your standard file upload form. With the Vercel AI SDK, tool results stream directly into your UI components. You can build a file browser that populates in real-time by feeding the output of `list_blobs` directly into your React state. The result is a snappy, responsive user experience that feels completely integrated.

Build Reactive File UIs with this MCP Server

Connecting your Next.js or Svelte app is straightforward. You import `createMCPClient`, point it to your Vinkius URL, and pass the tools to `generateText`. The AI SDK handles the heavy lifting of streaming tool outputs, so you can focus on building the UI. This is about what your user sees. When they ask to see a file, the text appears on their screen character-by-character as it's downloaded via `get_blob`. When they delete a file using `delete_blob`, it vanishes from the UI instantly because the action and the interface update are part of the same AI-driven operation.

Secure, Single-Container Access

This MCP server is hard-coded to a single Azure Blob Container. That’s a feature, not a bug. It gives your AI client a very specific, sandboxed place to work, so you never have to worry about it accessing the wrong storage account or container. Authentication is handled by Vinkius. You get one endpoint token to put in your environment variables, and that's it. No need to juggle Azure service principals or connection strings in your frontend code, which is great for security, especially when deploying to Edge Functions. Your agent can `list_blobs` and `get_blob`, but only within the walls you've defined.

Setup guide

Set up Azure Blob Container 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 Azure Blob Container 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 Azure Blob Container 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 Azure Blob Container. 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 Azure Blob Container 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 Azure Blob Container MCP in Vercel AI SDK

Invoke `streamText` with a prompt like "list all text files." The Vercel AI SDK will call the `list_blobs` tool from this MCP server and stream the file names back. You can feed this stream directly into a state variable to update your React or Svelte UI in real-time.

Yes. Your agent can use the `put_blob` tool. Just give the AI the file content and a destination path, and the tool uploads it to your configured container. It's ideal for letting users save generated text or data.

Absolutely. The `delete_blob` tool gives your agent the ability to remove files. Since this action is permanent, we recommend building a confirmation dialog in your UI before letting the agent proceed with the call.

Yes, it's fully compatible. Both the AI SDK and the MCP client are designed to run in edge environments. This lets you perform file operations with extremely low latency by executing the logic close to your users.

This server only touches the single Azure Blob Container you configure it with. All communication is encrypted over HTTPS. Vinkius processes your file contents and metadata ephemerally in a zero-trust sandbox and does not log or store any of it.

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