How to Use the Maestra MCP in Claude Code

Q: Can I get a list of all my Maestra files in the terminal with Claude Code?

Yes. Just run claude maestra-mcp listmaestrafiles. You can pipe the JSON output to a tool like jq to filter, sort, or transform the data for use in other shell scripts.

Q: How do I handle asynchronous jobs with Claude Code and Maestra?

You write a simple shell script. First, call uploadmediafortranscription. Then, use a while loop that calls getfiledetails every few seconds and checks the status field until it's no longer 'processing'.

Put video localization in your CI/CD pipeline. Claude Code connects your shell scripts and cron jobs directly to the Maestra API.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Maestra MCP to Claude Code

Create your Vinkius account to connect Maestra 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 Maestra with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless Transcription and Translation

This MCP Server lets you run Maestra's localization tools from any terminal. You can pipe a list of public video URLs to a script that calls `upload_media_for_transcription` for each one. It's designed for headless environments where there's no UI. You can chain commands in a single shell script. For example, upload a file, poll its status using `get_file_details` in a loop, and then trigger `translate_transcription` once the initial transcription is complete. It's perfect for automating nightly builds of training materials.

Automate Media Workflows in your MCP Server

Use this server to build solid automation. You can create a cron job that runs daily, calls `list_maestra_files`, and checks for any videos that were uploaded but never translated. This means no more manual checks or spreadsheets. You can pipe the output of one command directly into another. Get a list of file IDs, then pass them to a script that calls `export_transcription_results` to back up all your text data to a local disk. This is all about building reliable, repeatable processes.

Generate Voiceovers from the Command Line

Integrate AI voice generation into your deployment scripts. After a new product tutorial is translated with `translate_transcription`, your script can immediately generate the audio for all target languages as a next step. First, call `list_available_ai_voices` to get the voice IDs you need for each language. Then, trigger `generate_ai_voiceover` for each one. You can automate the creation of dozens of audio files as part of a single GitHub Action.

Setup guide

Set up Maestra 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 maestra-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http maestra-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 Maestra 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": {
    "maestra-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 Maestra. 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 Maestra 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 Maestra MCP in Claude Code

In your workflow YAML, install Claude Code, add the Maestra MCP server with `claude mcp add`, and then call the tools. For example: `claude maestra-mcp upload_media_for_transcription --url $VIDEO_URL`. The output can be used in subsequent steps.

Yes. Just run `claude maestra-mcp list_maestra_files`. You can pipe the JSON output to a tool like `jq` to filter, sort, or transform the data for use in other shell scripts.

You write a simple shell script. First, call `upload_media_for_transcription`. Then, use a `while` loop that calls `get_file_details` every few seconds and checks the `status` field until it's no longer 'processing'.

This MCP server handles authentication, token management, and provides a consistent command structure for all tools. You don't have to write custom `curl` commands, manage headers, or parse different API responses for every endpoint. It's a standard interface that just works.

The server only sees the media URLs and text content being processed. Your connection to the Vinkius-hosted MCP server is encrypted, and your Maestra API key is stored on that server, not in your CI/CD environment variables or shell history. This reduces its exposure.

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