Video Digest MCP server

This MCP Video Digest server extracts and transcribes audio from videos on platforms like YouTube, Bilibili, TikTok, and Twitter. It supports multiple transcription service providers including Deepgram, Gladia, Speechmatics, and AssemblyAI, with the flexibility to choose providers based on configured API keys.

Installation

Prerequisites

First, install uv (a Python package manager):

curl -LsSf https://astral.sh/uv/install.sh | sh

Setup Process

1. Clone the repository:

git clone https://github.com/R-lz/mcp-video-digest.git
cd mcp-video-digest

2. Create and activate a virtual environment:

uv venv
source .venv/bin/activate  # Linux/Mac
# or
.venv\Scripts\activate     # Windows

3. Install dependencies:

uv pip install -e .

Configuration

Create an .env file in the project root directory or rename the existing example:

mv .env.example .env

Edit the .env file to add your API keys:

DEEPGRAM_API_KEY=your_deepgram_key
GLADIA_API_KEY=your_gladia_key
SPEECHMATICS_API_KEY=your_speechmatics_key
ASSEMBLYAI_API_KEY=your_assemblyai_key

Note: You need to configure at least one service API key. The service priority order is:

• Deepgram (recommended for Chinese content)
• Gladia
• Speechmatics
• AssemblyAI

Usage

Starting the Server

Start the MCP server:

uv run src/main.py

Or run in debug mode:

UV_DEBUG=1 uv run src/main.py

Using the Client

Call the service using the MCP client:

from mcp.client import MCPClient

async def process_video():
    client = MCPClient()
    result = await client.call(
        "get_video_content",
        url="https://www.youtube.com/watch?v=video_id"
    )
    print(result)

Client SSE Example

Configure your client with:

{
    "mcpServers": {
      "video_digest": {
        "url": "http://<ip>:8000/sse"
    }
  }
}

You can also pass API keys in the client:

"env": {
   "DEEPGRAM_API_KEY":"your_deepgram_key"
}

Testing

Run the test script to verify functionality:

uv run test.py
# or
python test.py

This will:

• Validate environment variable configuration
• Test YouTube download functionality
• Test each transcription service
• Test the complete video processing pipeline

Service API Providers

Available transcription services with free tiers:

• Speechmatics: 8 free hours per month - Pricing
• Gladia: 10 free hours per month - Pricing
• AssemblyAI: $50 free credit - Pricing
• Deepgram: $200 free credit - Pricing

Important Notes

1. Ensure sufficient disk space for temporary files
2. Be aware of API usage limits for each provider
3. Python 3.11 or higher is recommended
4. For YouTube downloads requiring authentication, you can copy cookies to cookies.txt in the root directory

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.