How to Use the CaptionHub MCP in Mastra AI

Q: How do I add the CaptionHub MCP Server to Mastra AI?

Install @mastra/mcp@latest. Initialize a new MCPClient, pass your endpoint URL into the servers object, and call mcpClient.listTools() to spread the localization functions into your agent's toolkit.

Q: How do I require human approval for CaptionHub actions in Mastra AI?

Set requireToolApproval: true on destructive functions like archiving projects or approving captions. The workflow will suspend execution and wait for an external system to grant permission before the MCP Server proceeds.

Build resilient video localization pipelines with Mastra AI and the CaptionHub MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CaptionHub MCP to Mastra AI

Create your Vinkius account to connect CaptionHub 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 CaptionHub with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate localization workflows with Mastra AI

Video transcription fails sometimes. Networks drop, APIs timeout, and source files get corrupted. You can build a Mastra AI workflow that calls `transcribe_video` and automatically retries with exponential backoff if the job stalls. Your pipeline keeps running without human intervention. Conditional branching makes complex routing simple. When a new video hits your system, the agent uses `create_project` to set up the workspace. Spotting a Spanish source file triggers one set of metadata via `update_project`. For French audio, the MCP Server routes the job to a completely different review queue.

Add human-in-the-loop for caption approval

You do not want an autonomous agent finalizing public-facing subtitles on its own. By enabling Mastra's `requireToolApproval` setting, you force the workflow to pause right before calling `approve_captions`. A human reviewer checks the text, clicks approve, and the agent resumes execution. The system pulls project context automatically. Before asking for permission, the agent can run `get_project_details` and `export_captions` to generate a preview link. The reviewer sees exactly what they are approving without logging into a separate dashboard.

Maintain clean workspaces autonomously

Stale projects clutter up your account limits. You can deploy a scheduled Mastra agent that runs `list_projects` every Friday at midnight. It identifies anything inactive for over ninety days and permanently deletes it using `archive_project`. Infrastructure monitoring happens in the background. The agent checks `get_account_info` to track usage quotas and pulls `list_webhooks` to verify your external notifications are still firing correctly. You deploy this once to your cloud provider and forget about it.

Setup guide

Set up CaptionHub 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 CaptionHub 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: "captionhub-mcp-client",
  servers: {
    "captionhub-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent CaptionHub 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 CaptionHub. 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 CaptionHub 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 CaptionHub MCP in Mastra AI

Install `@mastra/mcp@latest`. Initialize a new `MCPClient`, pass your endpoint URL into the `servers` object, and call `mcpClient.listTools()` to spread the localization functions into your agent's toolkit.

Mastra's built-in workflow engine lets you wrap the transcription trigger in a retry block. If the API rejects the request, the agent waits and tries again based on your configured backoff schedule.

The client auto-detects the best transport method available. It will default to Streamable HTTP or SSE to keep the connection alive while waiting for long-running video project updates.

Set `requireToolApproval: true` on destructive functions like archiving projects or approving captions. The workflow will suspend execution and wait for an external system to grant permission before the MCP Server proceeds.

The system processes your subtitle tracks, webhook configurations, and project metadata through a zero-trust Vinkius container. Every command executes in a temporary sandbox that wipes all memory the second the workflow step completes.

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