How to Use the Mux MCP in Vercel AI SDK

Q: How do I connect the Mux MCP Server to the Vercel AI SDK?

Install @ai-sdk/mcp and set up your HTTP transport. Call createMCPClient with the Vinkius endpoint, then pass mcpClient.tools() into streamText. Always run mcpClient.close() when the session ends.

Q: Can Vercel AI SDK stream Mux upload progress to a React component?

Yes. Your agent can call createdirectupload to generate a signed URL. You pass that URL to your client-side uploader component to handle the actual file transfer.

Q: How do I list existing Mux videos in my Vercel AI SDK app?

The agent executes listassets to pull your media library. It filters the results and streams a formatted list of video IDs directly into your chat interface.

Build live video applications where your Vercel AI SDK frontend connects to this MCP Server and streams Mux assets straight to the user.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mux MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Streaming Video Asset Creation

Your users want to upload videos without leaving the chat interface. The Vercel AI SDK connects to this MCP Server and calls `create_direct_upload` in the background. The agent gets a secure upload URL and passes it straight to your Next.js frontend. Once the upload finishes, the agent can trigger `create_asset` to process the file. Your UI updates instantly. No loading spinners. Just raw video data flowing into your React components as the tools execute.

Real-Time Analytics UI

Video analytics usually live in a dashboard nobody checks. Bring them directly into your user's workflow. The agent uses `get_recent_views` to pull playback metrics for any specific video. Vercel's streaming architecture means the agent can fetch `get_asset` details and render a custom UI component with the view count immediately. You build the frontend component, and the MCP Server handles the data fetching.

Live Stream Generation via Vercel AI SDK

Launching a broadcast takes exactly one prompt. Your AI client calls `create_live_stream` and receives the RTMP ingest details back from Mux. You don't have to write backend wrappers for the API. The agent grabs the stream key and playback ID, then formats them for your user. If they need to check the status later, `get_live_stream` pulls the active connection state.

Setup guide

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

Install `@ai-sdk/mcp` and set up your HTTP transport. Call `createMCPClient` with the Vinkius endpoint, then pass `mcpClient.tools()` into `streamText`. Always run `mcpClient.close()` when the session ends.

Yes. Your agent can call `create_direct_upload` to generate a signed URL. You pass that URL to your client-side uploader component to handle the actual file transfer.

The SDK streams the tool call state to the frontend. Your users see that the agent is actively setting up the Mux infrastructure, rather than wondering if the app froze.

The agent executes `list_assets` to pull your media library. It filters the results and streams a formatted list of video IDs directly into your chat interface.

The server only handles metadata, stream keys, and analytics data. The actual video bytes never pass through the AI provider. Vinkius isolates the execution environment, keeping your Mux account credentials strictly secure.

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