How to Use the Kapwing MCP in Mastra AI

Q: How do I register the Kapwing server in Mastra AI?

Initialize a new MCPClient and pass the server URL in the servers object. Then call listTools() and spread the result into your agent's tool array. Mastra automatically detects if the transport is SSE or Streamable HTTP.

Q: How do I handle human approval before generating a Kapwing video?

Set requireToolApproval to true for the creation tool. The workflow pauses execution, asks a human to review the JSON dimensions and layers, and only proceeds when authorized.

Build resilient, automated Kapwing video generation workflows using this MCP Server and Mastra AI.

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 Mastra AI

Create your Vinkius account to connect Kapwing to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Orchestrate Media Pipelines in Mastra AI

The `create_render` tool turns a JSON project definition into an active video generation job. It accepts width, height, and layer configurations to construct the final asset. Your workflow dictates exactly what goes into that payload based on upstream data. Mastra handles the execution logic. If the initial API call times out, the framework's exponential backoff automatically retries the request without manual intervention. You get reliable media creation even under heavy network load.

Manage Long-Running Render Jobs

Grabbing the final video URL requires the `get_render_status` tool, which targets a specific render ID. Video generation takes time, and this endpoint provides the current progress state. You can build a conditional branch that loops this status check. If the status returns as pending, the workflow pauses and checks again later. Once complete, the branch advances and sends the download link to your notification channel.

Audit Account Assets via MCP

Returning your entire video history is the job of the `list_renders` tool. It fetches all associated projects linked to the authenticated account. This is useful for cleanup or audit workflows. An agent can pull the list, identify duplicate renders based on metadata, and flag them for review. You automate asset management without writing one-off scripts.

Setup guide

Set up Kapwing MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Kapwing tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "kapwing-mcp-client",
  servers: {
    "kapwing-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Kapwing Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Kapwing tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Kapwing transactions"
);
console.log(result.text);

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 Mastra AI

Initialize a new `MCPClient` and pass the server URL in the servers object. Then call `listTools()` and spread the result into your agent's tool array. Mastra automatically detects if the transport is SSE or Streamable HTTP.

The framework natively supports exponential backoff for tool calls. If the rendering endpoint throws a 500 error, the agent waits and tries the exact same JSON payload again.

Set `requireToolApproval` to true for the creation tool. The workflow pauses execution, asks a human to review the JSON dimensions and layers, and only proceeds when authorized.

It operates over Streamable HTTP or SSE, depending on your client setup. The framework handles the connection details automatically.

The Vinkius infrastructure routes your project dimensions, text layers, and media URLs through a sandboxed environment that destroys itself after execution. We don't store your video content. Your API tokens remain encrypted and are only exposed during the active HTTP request.

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