DeepSRT MCP server

The DeepSRT MCP server provides YouTube video summarization functionality by integrating with DeepSRT's API. This server follows the Model Context Protocol (MCP) standard, allowing AI assistants to generate summaries of YouTube videos in different languages and formats.

Installation

Setting Up for Claude Desktop

1. Install dependencies and build the server:

npm install
npm run build

2. Configure Claude Desktop by adding the server details to your config file:

macOS location:

~/Library/Application Support/Claude/claude_desktop_config.json

Windows location:

%APPDATA%/Claude/claude_desktop_config.json

Add this configuration to your file:

{
  "mcpServers": {
    "deepsrt-mcp": {
      "command": "node",
      "args": [
        "/path/to/deepsrt-mcp/build/index.js"
      ]
    }
  }
}

Setting Up for Cline

For Cline users, installation is much simpler. Just ask Cline in chat:

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

Cline will automatically install the server and update your cline_mcp_settings.json.

Usage

Available Tool: get_summary

This tool generates summaries for YouTube videos.

Parameters:

• videoId (required): The YouTube video ID
• lang (optional): Language code for the summary (defaults to zh-tw)
• mode (optional): Summary format - either "narrative" or "bullet" (defaults to narrative)

Examples

Using with Claude Desktop:

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

Using with Cline:

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

How It Works

Content Caching Process

For the server to work properly, videos need to be cached in DeepSRT's system:

1. Initial Caching: Open the video through DeepSRT's service to ensure it's cached
2. MCP Retrieval: Once cached, summaries can be fetched quickly through MCP
3. Pre-cached Content: Some videos may already be cached from previous users, but this isn't guaranteed

Troubleshooting

If you receive a 404 error, it likely means the video hasn't been cached yet. To resolve this:

1. Open the video using the DeepSRT Chrome extension
2. This will cache the content in the CDN network
3. After caching, the MCP server should be able to retrieve the summary

You can verify the cache status with cURL:

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

If you see cache-status: HIT, the content is properly cached and your MCP server should work correctly.

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.