How to Use the CaptionHub MCP in VS Code Copilot

Q: Can VS Code Copilot trigger CaptionHub transcriptions directly?

Yes, the agent can execute the transcribevideo tool right from the chat panel. It passes the required project ID and starts the background job. You see the confirmation instantly.

Bring CaptionHub into VS Code Copilot. Give your entire engineering team live access to video localization data directly in their editor.

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 VS Code Copilot

Create your Vinkius account to connect CaptionHub to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy the CaptionHub MCP Server team-wide.

Enterprise teams need consistent tooling across every developer machine. You drop the MCP configuration into your `.vscode/mcp.json` file. Everyone who clones the repository instantly gets the ability to interact with the localization API. Onboarding new engineers gets significantly easier. They just open Copilot Chat and ask to see the active translation tasks. The agent runs `list_projects` and `get_project_details` to show them exactly how the data models work in production.

Automate your video workflows.

Building media pipelines means testing a lot of state transitions. Your AI client can spin up test runs by executing `create_project` followed by `transcribe_video`. Developers watch the real API respond instead of reading outdated Swagger docs. Handling the final output requires exact URL structures. Copilot uses `export_captions` to fetch the real subtitle links. It then writes the exact parsing logic your backend needs to ingest those VTT or SRT files.

Audit system health and clean up tests.

Stale test data creates confusion in shared staging environments. Developers can tell their editor to clean up after themselves using `archive_project`. This keeps the main platform dashboard clear of junk entries. Infrastructure engineers also need visibility into the event system. Running `list_webhooks` lets them verify that notification endpoints are correctly registered. They can also check `get_account_info` to ensure the team has enough quota for the current sprint.

Setup guide

Set up CaptionHub MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the CaptionHub MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the CaptionHub tools listed. Try asking: "List my recent CaptionHub transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "captionhub-mcp": {
      "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 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 VS Code Copilot

Add the Vinkius URL to your workspace's .vscode/mcp.json file. Commit that file to your Git repository. Every developer on the team will automatically inherit the configuration.

Yes, the agent can execute the `transcribe_video` tool right from the chat panel. It passes the required project ID and starts the background job. You see the confirmation instantly.

You must switch the chat interface into Agent mode. Standard Copilot only reads your local files and cannot execute external tools. Click the Agent icon in the chat input box to enable remote execution.

No, the integration uses the native Model Context Protocol built into recent editor updates. As long as your team runs version 1.96 or higher, the tools work out of the box.

Vinkius processes all tool executions inside an ephemeral, zero-trust V8 Isolate Sandbox. The system reads project metadata, webhook URLs, and caption text strictly during the active request. No proprietary localization data is retained after the connection closes.

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