How to Use the Dyte MCP in Cursor

Q: How do I add the Dyte server to my Cursor project config?

Create a .cursor/mcp.json file in your project root and add the MCP Server configuration. Once saved, the Cursor agent can immediately call tools like meeting creation during your coding sessions.

Q: How do I stop a live broadcast from the editor?

Ask the agent to run stoplivestream for your active meeting ID. The editor executes the tool and updates your local UI state to reflect that the feed has ended.

Generate real video rooms and inject participant tokens directly into your Cursor codebase using live API data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dyte MCP to Cursor

Create your Vinkius account to connect Dyte to Cursor 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 Dyte with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate live Dyte meetings directly in Cursor

This MCP Server exposes `create_meeting` so your Cursor agent can spin up real video rooms while writing your video application code. Instead of writing mock endpoints, your editor calls the live API and injects actual meeting IDs into your source files. You can quickly check the configuration of any video room by letting the Cursor agent call `get_meeting`. This pulls the exact payload structure into your editor, helping you map database schemas without leaving your workspace.

Inject live participant tokens into Cursor files

The `add_participant` tool lets your Cursor agent fetch authentic video join tokens and write them directly into your local testing files. You don't have to copy-paste tokens from an external dashboard to test your client-side video player. When debugging active video sessions, the Cursor agent calls `list_participants` to see who is currently connected. It displays the active roster right inside your editor chat, letting you verify connection states in real time.

Test recording workflows inside Cursor

This MCP Server connects `start_recording` and `stop_recording` directly to your Cursor development environment for testing video archives. You can trigger live recordings from the chat panel to verify how your app handles webhook payloads. The Cursor agent can also run `get_recording` to pull down the final video file metadata. This lets you write and test your post-meeting processing scripts with actual production file paths.

Setup guide

Set up Dyte MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Dyte MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Dyte transactions." If the MCP tools are loaded correctly, Cursor will call the Dyte tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "dyte-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 Dyte. 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 Dyte 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 Dyte MCP in Cursor

Create a `.cursor/mcp.json` file in your project root and add the MCP Server configuration. Once saved, the Cursor agent can immediately call tools like meeting creation during your coding sessions.

Yes, Composer can orchestrate multi-file changes using live data from tools like `list_meetings`. This lets the agent scaffold a complete video dashboard using real room data.

Yes, the MCP Server runs the tools locally to interact with your active development server. You can test webhook endpoints by calling `create_webhook` directly from your editor chat.

Ask the agent to run `stop_livestream` for your active meeting ID. The editor executes the tool and updates your local UI state to reflect that the feed has ended.

Your API credentials and meeting metadata are stored in your local configuration files and never sent to external indexing servers. The tools execute inside a secure local sandbox, ensuring your private meeting details stay private.

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