Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT and other tools is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AI Fire in da houseCheck it out free

deepsrt-mcp

MCP.Pizza Chef: DeepSRT

DeepSRT MCP Server is an MCP server that enables YouTube video summarization by integrating with DeepSRT's API. It supports narrative and bullet-point summary modes and multiple languages, with a default of Traditional Chinese (zh-tw). The server caches video content via DeepSRT to ensure fast summary retrieval from CDN edge locations, providing efficient and seamless integration within MCP-enabled environments for real-time video content summarization.

Use This MCP server To

Generate narrative summaries for YouTube videos Create bullet-point summaries for video content Retrieve video summaries in multiple languages Cache YouTube video content for faster summary access Integrate video summarization into MCP-enabled apps Serve summaries from CDN edge locations for low latency Support multi-language video content summarization workflows

README

DeepSRT MCP Server

A Model Context Protocol (MCP) server that provides YouTube video summarization functionality through integration with DeepSRT's API.

Features

  • Generate summaries for YouTube videos
  • Support for both narrative and bullet-point summary modes
  • Multi-language support (default: zh-tw)
  • Seamless integration with MCP-enabled environments

How it Works

  1. Content Caching

    • Videos must first be opened through DeepSRT to ensure content is cached in the service
    • This initial viewing triggers the caching process in the DeepSRT service
  2. MCP Summary Retrieval

    • When requesting summaries through MCP, the content is served from DeepSRT's CDN edge locations
    • This ensures fast and efficient delivery of summaries
  3. Pre-cached Content

    • Some videos may already be cached in the system from previous user requests
    • While you might be able to fetch summaries for these pre-cached videos, availability is not guaranteed
    • For best results, ensure videos are first opened through DeepSRT
%%{init: {'theme': 'dark', 'themeVariables': { 'primaryColor': '#2496ED', 'secondaryColor': '#38B2AC', 'tertiaryColor': '#1F2937', 'mainBkg': '#111827', 'textColor': '#E5E7EB', 'lineColor': '#4B5563', 'noteTextColor': '#E5E7EB'}}}%%
sequenceDiagram
    participant User
    participant DeepSRT
    participant Cache as DeepSRT Cache/CDN
    participant MCP as MCP Client

    Note over User,MCP: Step 1: Initial Caching
    User->>DeepSRT: Open video through DeepSRT
    DeepSRT->>Cache: Process and cache content
    Cache-->>DeepSRT: Confirm cache storage
    DeepSRT-->>User: Display video/content

    Note over User,MCP: Step 2: MCP Summary Retrieval
    MCP->>Cache: Request summary via MCP
    Cache-->>MCP: Return cached summary from edge location

    Note over User,MCP: Alternative: Pre-cached Content
    rect rgba(31, 41, 55, 0.6)
        MCP->>Cache: Request summary for pre-cached video
        alt Content exists in cache
            Cache-->>MCP: Return cached summary
        else Content not cached
            Cache-->>MCP: Cache miss
        end
    end
Loading

Installation

Installing for Claude Desktop

  1. First, build the server:
npm install
npm run build
  1. Add the server configuration to your Claude Desktop config file:
  • On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "deepsrt-mcp": {
      "command": "node",
      "args": [
        "/path/to/deepsrt-mcp/build/index.js"
      ]
    }
  }
}

Installing for Cline

Just ask Cline to install in the chat:

"Hey, install this MCP server for me from https://github.com/DeepSRT/deepsrt-mcp"

Cline will auto install deepsrt-mcp for you and update your cline_mcp_settings.json.

Usage

The server provides the following tool:

get_summary

Gets a summary for a YouTube video.

Parameters:

  • videoId (required): YouTube video ID
  • lang (optional): Language code (e.g., zh-tw) - defaults to zh-tw
  • mode (optional): Summary mode ("narrative" or "bullet") - defaults to narrative

Example Usage

Using Claude Desktop:

// The MCP tool will fetch the video summary
const result = await mcp.use_tool("deepsrt-mcp", "get_summary", {
  videoId: "dQw4w9WgXcQ",
  lang: "zh-tw",
  mode: "narrative"
});

Using Cline:

const result = await mcp.use_tool("deepsrt", "get_summary", {
  videoId: "dQw4w9WgXcQ",
  lang: "zh-tw",
  mode: "bullet"
});

Development

Install dependencies:

npm install

Start development server:

npm run dev

Build for production:

npm run build

Demo

FAQ

Q: I am getting 404 error, why?

A: This is because the video summary is not cached in the CDN edge location, you need to open this video using DeepSRT chrome extension to have it cached in the CDN network before you can get that summary using MCP.

You can verify the cache status using cURL like this

curl -s 'https://worker.deepsrt.com/transcript' \
-i --data '{"arg":"v=VafNvIcOs5w","action":"summarize","lang":"zh-tw","mode":"narrative"}' | grep -i "^cache-status"
cache-status: HIT

If you see cache-status: HIT the content is cached in the CDN edge location and your MCP server shoud not get 404.

deepsrt-mcp FAQ

How does DeepSRT MCP server cache video content?
Videos must be opened through DeepSRT first to trigger caching in the DeepSRT service, enabling faster summary retrieval.
Can I get summaries in languages other than Traditional Chinese?
Yes, the server supports multi-language summaries with Traditional Chinese as the default, allowing flexible language options.
How does the server ensure fast delivery of summaries?
Summaries are served from DeepSRT's CDN edge locations, reducing latency and improving response times.
Is it possible to get summaries for videos not previously cached?
Summaries for pre-cached videos may be available, but for best results, videos should be opened through DeepSRT to ensure caching.
How does this MCP server integrate with MCP-enabled environments?
It provides a seamless API interface that MCP clients can call to request video summaries within their workflows.
What summary formats does DeepSRT MCP server support?
It supports both narrative and bullet-point summary modes to suit different user preferences.
Does the server support real-time summarization?
The server relies on cached content for summary generation, so real-time summarization depends on prior caching through DeepSRT.
Can this server be used for videos outside YouTube?
The server is designed specifically for YouTube video summarization via DeepSRT's API integration.