How to Use the CaptionHub MCP in Vercel AI SDK

Q: How do I connect CaptionHub to Vercel AI SDK?

Pass your endpoint into createMCPClient({ transport: { type: "http", url: "..." } }). Call mcpClient.tools() to expose the localization functions to your model. Remember to call mcpClient.close() when the session ends.

Q: Can the Vercel AI SDK stream CaptionHub project updates live?

When your agent calls getprojectdetails, the response streams back to your React or Svelte frontend piece by piece. Users see the translation status update before the full JSON payload finishes loading.

Q: How do I handle authentication for CaptionHub in Vercel AI SDK?

Vinkius handles the underlying API keys. You just pass an authProvider configuration during your MCP client setup to route requests through your managed endpoint securely.

Stream live video localization data into your React apps with the CaptionHub MCP Server and Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect CaptionHub to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build fast localization UIs with Vercel AI SDK

Your end users hate waiting for progress bars. When they need to check translation status, you want that data appearing instantly in the browser. Using the `list_projects` and `get_project_details` tools, your Next.js frontend streams the exact state of every video localization job right to the screen. You do not need to build custom polling logic. The MCP integration handles the connection while your AI model formats the incoming payload. If a user asks for their export link, the agent fires `export_captions` and the download URL renders live in your chat interface.

Trigger AI transcription from the edge

Kicking off an audio transcription job usually requires a messy backend queue. Now you just wire up `transcribe_video` to your user-facing prompt. A user clicks a button, the Vercel AI SDK catches the intent, and the agent initiates the auto-transcription process immediately. You get immediate feedback on the job creation. Instead of writing separate API routes to handle project setup, your agent uses `create_project` and updates metadata via `update_project` in one fluid motion. The user watches the agent confirm the configuration step by step.

Manage human approvals in real-time

Video translation requires human sign-off. You can build a custom dashboard where managers review text and type their confirmation into your chat UI. The agent interprets the command and executes `approve_captions` for that specific language track. Archiving old work happens just as fast. When a season wraps up, the user tells your app to clean up the workspace. The agent pulls the active webhooks with `list_webhooks`, checks account limits via `get_account_info`, and permanently removes dead campaigns using `archive_project`.

Setup guide

Set up CaptionHub MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all CaptionHub tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent CaptionHub transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Pass your endpoint into `createMCPClient({ transport: { type: "http", url: "..." } })`. Call `mcpClient.tools()` to expose the localization functions to your model. Remember to call `mcpClient.close()` when the session ends.

When your agent calls `get_project_details`, the response streams back to your React or Svelte frontend piece by piece. Users see the translation status update before the full JSON payload finishes loading.

The standard HTTP transport works perfectly in Vercel Edge environments. You just need to ensure your AI model provider supports edge execution for tool calling.

Vinkius handles the underlying API keys. You just pass an `authProvider` configuration during your MCP client setup to route requests through your managed endpoint securely.

Your raw video files, caption text, and project metadata route through an isolated V8 sandbox on Vinkius. The MCP Server processes the request ephemerally and destroys the environment immediately after returning the export URLs or transcription status.

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