How to Use the Cloudflare Stream MCP in Vercel AI SDK

Q: How do I connect Cloudflare Stream to a Vercel AI SDK project?

Install @ai-sdk/mcp and initialize the Cloudflare Stream client using createMCPClient with your Vinkius HTTP URL. Pass the tools array from mcpClient.tools() into streamText to let your React app invoke video tools.

Q: Is it possible to stream live video configurations using Cloudflare Stream and Vercel AI SDK?

Yes, your Vercel AI SDK app calls createliveinput to generate Cloudflare Stream ingestion endpoints, then streams those RTMP details directly into your UI.

Q: How does Vercel AI SDK handle long-running Cloudflare Stream uploads?

The Vercel AI SDK agent initiates the process with initiateupload using the TUS protocol, returning the Cloudflare Stream upload URL to the browser to handle the heavy upload.

Q: Does the Vercel AI SDK agent manage security keys for my videos?

Yes, the Vercel AI SDK agent uses createsigningkey and listsigningkeys to manage secure playback tokens for your Cloudflare Stream videos.

Build live-updating video portals where your Vercel AI SDK app controls Cloudflare Stream directly using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cloudflare Stream MCP to Vercel AI SDK

Create your Vinkius account to connect Cloudflare Stream 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 Cloudflare Stream with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time video player controls in Vercel AI SDK

This Cloudflare Stream MCP Server lets your Vercel AI SDK application query video files and display live status updates instantly. It's easy to call `get_video` or `list_videos` to get details, feeding raw Cloudflare video metadata directly into your Next.js stream as it processes. When users request offline access, your Vercel AI SDK frontend triggers `create_mp4_download` or `create_m4a_download` to modify the Cloudflare Stream resource. You'll see downloadable links render in your React UI the millisecond the Cloudflare CDN generates them, preventing layout shifts.

Live stream dashboard management in React

Manage live broadcasts on the fly by letting your Vercel AI SDK agent configure feeds using Cloudflare Stream `create_live_input` and `create_live_output` tools. Your Next.js frontend displays the resulting RTMP ingestion URLs and stream keys immediately without waiting for a full page reload. If the user stops the broadcast, the Vercel AI SDK client calls `delete_live_input` or `delete_live_output` to clean up the active Cloudflare Stream endpoints. Everything runs inside lightweight Edge Functions, keeping your video streaming cold starts under 50ms.

On-demand asset processing and captions

Handle video uploads directly from the browser using the TUS protocol via `initiate_upload` within your Vercel AI SDK application. Your Next.js agent monitors the upload progress and triggers Cloudflare Stream `generate_caption` as soon as the file lands. To customize the viewer experience, the Vercel AI SDK agent calls `upload_caption` or `create_watermark` based on real-time user inputs. The Cloudflare Stream player updates dynamically, letting creators see their branding applied in their active React session.

Setup guide

Set up Cloudflare Stream 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 Cloudflare Stream 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 Cloudflare Stream 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 Cloudflare Stream. 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 Cloudflare Stream 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 Cloudflare Stream MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and initialize the Cloudflare Stream client using `createMCPClient` with your Vinkius HTTP URL. Pass the tools array from `mcpClient.tools()` into `streamText` to let your React app invoke video tools.

Yes, your Vercel AI SDK app calls `create_live_input` to generate Cloudflare Stream ingestion endpoints, then streams those RTMP details directly into your UI.

The Vercel AI SDK agent initiates the process with `initiate_upload` using the TUS protocol, returning the Cloudflare Stream upload URL to the browser to handle the heavy upload.

Yes, the Vercel AI SDK agent uses `create_signing_key` and `list_signing_keys` to manage secure playback tokens for your Cloudflare Stream videos.

Your Cloudflare Stream API tokens and video configurations never persist on the Vinkius MCP host, which runs inside secure, ephemeral V8 isolates.

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