Official MCP Server for tl;dv API

The First and Only MCP Server for Google Meet, Zoom, and Microsoft Teams Integration

This project provides a Model Context Protocol (MCP) server enabling seamless interaction with the tl;dv API. As the pioneering MCP solution for video conferencing platforms, it unlocks the power of tl;dv's meeting intelligence across Google Meet, Zoom, and Microsoft Teams through a standardized interface. This integration allows AI models and MCP clients to access, analyze, and derive insights from your meetings across all major platforms in one unified way.

Features

• List Meetings: Retrieve meetings based on filters (query, date range, participation status, type) across all supported platforms.
• Get Meeting Metadata: Fetch detailed information for a specific meeting by ID, regardless of the platform it was hosted on.
• Get Transcript: Obtain the transcript for any meeting ID, with consistent formatting across all platforms.
• Get Highlights: Retrieve AI-generated highlights for meetings from any supported platform.
• Import Meeting (Coming Soon): Functionality to import meetings via URL from any supported platform.

Prerequisites

• tl;dv Account: A Business or Enterprise tl;dv account is required.
• tl;dv API Key: You need an API key, which can be requested from your tl;dv settings: https://tldv.io/app/settings/personal-settings/api-keys.
• Node.js & npm (for Node installation): If installing via Node.js, ensure Node.js and npm are installed.
• Docker (for Docker installation): If installing via Docker, ensure Docker is installed and running.

Installation and Configuration

Step 1: Set up your API key

Create a .env file in the project root with your tl;dv API key:

cp .env.example .env

Edit the .env file and add your key:

TLDV_API_KEY=your_tldv_api_key_here

The .env file is git-ignored and never leaves your machine. This is the only place you need to store your API key -- the server automatically loads it at startup regardless of how it's launched.

Step 2: Build the server

Using Node.js

npm install
npm run build

Using Docker

docker build -t tldv-mcp-server .

Step 3: Configure your MCP client

Update your MCP client's configuration file (e.g., claude_desktop_config.json for Claude Desktop, or Cursor settings). No API key needed in the config -- it's already in your .env file.

Node.js config

{
  "mcpServers": {
    "tldv": {
      "command": "node",
      "args": ["/absolute/path/to/tldv-mcp-server/dist/index.js"]
    }
  }
}

Replace /absolute/path/to/tldv-mcp-server/dist/index.js with the actual path to the built server file.

Docker config

For Docker, the API key must be passed as an environment variable since the container doesn't have access to your local .env file:

{
  "mcpServers": {
    "tldv": {
      "command": "docker",
      "args": [
        "run", "-i", "--init", "--rm",
        "-e", "TLDV_API_KEY=<your-tldv-api-key>",
        "tldv-mcp-server"
      ]
    }
  }
}

Alternatively, mount your .env file into the container to avoid putting the key in the config:

{
  "mcpServers": {
    "tldv": {
      "command": "docker",
      "args": [
        "run", "-i", "--init", "--rm",
        "-v", "/absolute/path/to/tldv-mcp-server/.env:/app/.env:ro",
        "tldv-mcp-server"
      ]
    }
  }
}

Refer to your specific MCP client's documentation for detailed setup instructions (e.g., Claude Tools).

Disclaimer: After updating the config file, you will need to restart your MCP client for the changes to take effect.

Development

1. Install dependencies:

   npm install

2. Set up your .env file (if you haven't already):

   cp .env.example .env

   Edit .env and add your TLDV_API_KEY.

3. Run in development mode:

   npm run watch

4. Update client for local development: Configure your MCP client to use the local development server path (typically /path/to/your/project/dist/index.js). The server reads the API key from .env automatically.

5. Reload your MCP Client: Since the watch command recompiles on file changes, reloading your client (e.g., Claude Desktop) will pick up the latest version.

Debugging

• Console Logs: Check the console output when running npm run dev for detailed logs. The server uses the debug library; you can control log levels via environment variables (e.g., DEBUG=tldv-mcp:*).
• Node.js Debugger: Utilize standard Node.js debugging tools (e.g., Chrome DevTools Inspector, VS Code debugger) by launching the server process with the appropriate flags (e.g., node --inspect dist/index.js).
• MCP Client Logs: Check the logs provided by your MCP client, which might show the requests sent and responses received from this server.

Learn More

• tl;dv Developer API Documentation
• Model Context Protocol (MCP) Specification