How to Use the api.video MCP in Claude Code

Q: How do I configure the api.video integration inside Claude Code?

Run claude mcp add --transport http apivideo-mcp -- directly in your terminal. This command registers the MCP server inside your /.claude.json configuration file, letting your agent instantly call the media tools.

Control your entire video pipeline directly from your terminal by connecting this api.video MCP Server to Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect api.video MCP to Claude Code

Create your Vinkius account to connect api.video 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 api.video with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate video ingestion from your Claude Code terminal

Claude Code handles your files, so let it handle your uploads too. You can instruct your terminal agent to spin up a new hosting target using `create_video_object` and immediately get back the upload token. It cuts out the context switching of opening a browser to drop a file into a dashboard. If a build fails or an asset gets deprecated, you don't need to manually hunt down the file ID. Tell your command-line agent to call `delete_video` right inside your terminal session to clean up your staging environments.

Audit video performance using CLI-driven analytics

Sifting through video views shouldn't require logging into a heavy web UI. Your agent can query `get_video_analytics` to pull raw performance numbers directly into your terminal buffer. Pipe that output straight into your custom shell scripts or grep for specific drop-off patterns. You can also keep tabs on your library structure by running `list_videos` to filter assets by tags or titles. If you spot outdated titles during a quick terminal audit, your agent can fix them instantly with `update_video_details`.

Manage player themes and captions in headless scripts

Managing global brand assets shouldn't slow down your deployment scripts. This MCP Server lets your terminal agent run `list_player_themes` to verify that your videos use the correct branded player before they go live. If you are prepping localized content, your agent can check for translation gaps. Use `list_video_captions` and `list_video_chapters` to confirm that all required accessibility and navigation markers are in place before your release script finishes.

Setup guide

Set up api.video 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 apivideo-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http apivideo-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 api.video 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": {
    "apivideo-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 api.video. 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 api.video 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 api.video MCP in Claude Code

Run `claude mcp add --transport http apivideo-mcp -- ` directly in your terminal. This command registers the MCP server inside your `~/.claude.json` configuration file, letting your agent instantly call the media tools.

Yes, you can tell your terminal agent to script a loop over your assets. It will fetch your current library with `list_videos` and apply bulk changes using `update_video_details` without you writing a single line of Python.

The agent doesn't upload raw gigabytes through the LLM itself; instead, it uses `create_video_object` to generate the upload URL. You then feed that URL to your local curl commands or upload scripts right in your terminal.

Since you are running in the terminal, you can ask your agent to inspect the tool execution logs. If a call to `get_video_details` fails due to an invalid ID, the raw JSON error prints directly to your terminal standard output.

Your video details, player themes, and viewer metrics never touch third-party databases. The server runs in a secure, isolated sandbox on Vinkius, passing raw API payloads directly between your terminal client and the video platform.

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