How to Use the Kapwing MCP in Vercel AI SDK

Q: How do I connect Kapwing to the Vercel AI SDK?

Install the @ai-sdk/mcp package and define the HTTP transport URL. Pass the resulting tool array into your generateText or streamText function. Remember to call mcpClient.close() when the session ends.

Stream live Kapwing video generation status directly to your React frontend using this MCP Server and 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 Kapwing MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger Video Generation via MCP Server

The `create_render` tool accepts a raw JSON payload defining video dimensions and layers, kicking off the media build instantly. You pass the dimensions, text elements, and video clips directly from your user's prompt. Your agent handles the formatting. Vercel AI SDK streams this interaction straight to your Next.js frontend. The user watches the agent construct the payload in real-time, eliminating the need for loading spinners while the backend works.

Stream Live Render Progress

Checking job completion happens through the `get_render_status` tool. It takes the specific render ID and returns the current state along with the final download URL once finished. You don't have to build custom webhooks to know when a file is ready. Because you are using a streaming client, you can pipe these status updates into a live progress bar component. The agent polls the endpoint, and the UI updates continuously until the video file drops.

Fetch Historical Account Assets

Pulling past projects requires the `list_renders` tool, which grabs all media associated with your account. It returns the raw asset list for the agent to parse. If a user asks to see their recent marketing videos, the agent fetches the array and renders it into a grid component on the client side. You get a fully functional media gallery without writing dedicated database queries.

Setup guide

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

Install the `@ai-sdk/mcp` package and define the HTTP transport URL. Pass the resulting tool array into your `generateText` or `streamText` function. Remember to call `mcpClient.close()` when the session ends.

Yes, the agent can poll the status endpoint and stream the text response back to the client. You map that incoming stream to a React component state. The user sees the progress update live.

The HTTP transport layer works perfectly within Edge environments. Your application handles the tool calls without requiring a heavy Node.js backend.

The status tool returns the error state from the API. You can program your agent to read this failure and immediately stream an error message to the user, or attempt a retry with modified JSON.

Your JSON layer definitions and final MP4 URLs pass through an ephemeral V8 Isolate Sandbox. Vinkius operates on a zero-trust architecture, meaning it holds no memory of your video assets or text overlays once the connection terminates. Auth tokens map strictly to the isolated environment.

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