How to Use the Kapwing MCP in Claude Code

Q: Can I chain Kapwing tool calls together using Claude Code in a shell script?

Absolutely. You can store the render ID from createrender in a shell variable, then pass that variable to getrenderstatus inside a loop. This is a common pattern for automating render-and-download tasks.

Q: What's the best way to handle JSON with Claude Code and Kapwing?

Pipe it. Generate your JSON with another tool or script and pipe it into claude mcp call kapwing-mcp createrender. For parsing output from listrenders or getrenderstatus, pipe the result to jq.

Q: How do I connect Claude Code to the Kapwing server?

It's a single command: claude mcp add --transport http kapwing-mcp -- . After that, the tools are available immediately. Your config is saved in /.claude.json.

Q: What kind of data is exposed when automating Kapwing renders from my terminal?

Only the JSON project data for each render is sent through the MCP server to Kapwing's API. The connection is secured by your Vinkius token, and the server itself doesn't log or persist your project's content.

Automate video rendering in your CI/CD pipelines. Pipe JSON to Kapwing directly from the Claude Code terminal.

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 Claude Code

Create your Vinkius account to connect Kapwing to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Render Videos from the Command Line

The `create_render` tool takes a JSON payload and starts a Kapwing render job. You can pipe a JSON file directly to it or construct the payload within a shell script. It's built for headless automation. For example, you can set up a GitHub Action that generates a JSON file, then uses Claude Code to call `create_render`. The action gets back a render ID, which you can pass to the next step in your pipeline.

Script Your Render Status Checks

Use `get_render_status` with a render ID to poll for completion. The tool outputs the status and, once finished, the download URL. This is essential for any script that needs to wait for a video before continuing. Write a simple bash script that calls `create_render`, then loops and calls `get_render_status` every 10 seconds. Once the status is 'complete', the script can use `curl` to download the file and move on. Claude Code makes this trivial.

Manage Assets with this Claude Code MCP Server

The `list_renders` tool dumps a JSON array of all your previous renders. You can pipe this output to tools like `jq` to filter, search, and process your asset history right in the terminal. Set up a nightly cron job that runs `claude mcp call kapwing-mcp list_renders`, pipes the output to a script that checks for old or failed renders, and sends a notification. It's simple, reliable, and requires no UI.

Setup guide

Set up Kapwing MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see kapwing-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Kapwing transactions." It will automatically discover and invoke the available Kapwing tools.

Terminal

claude mcp add --transport http kapwing-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Kapwing MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "kapwing-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Code

In your workflow YAML, install Claude Code, add the Kapwing server, and then call the tools. For example, `claude mcp call kapwing-mcp create_render < project.json` to start a job, and then poll with `get_render_status`.

Absolutely. You can store the render ID from `create_render` in a shell variable, then pass that variable to `get_render_status` inside a loop. This is a common pattern for automating render-and-download tasks.

Pipe it. Generate your JSON with another tool or script and pipe it into `claude mcp call kapwing-mcp create_render`. For parsing output from `list_renders` or `get_render_status`, pipe the result to `jq`.

It's a single command: `claude mcp add --transport http kapwing-mcp -- `. After that, the tools are available immediately. Your config is saved in `~/.claude.json`.

Only the JSON project data for each render is sent through the MCP server to Kapwing's API. The connection is secured by your Vinkius token, and the server itself doesn't log or persist your project's content.

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