YouTube Comment Downloader MCP Server

by suckerfish

316 downloads
Not rated
GitHub

About

YouTube Comment Downloader MCP server that allows AI systems to download and analyze YouTube video comments without requiring API keys

Details

Author
suckerfish
Downloads
316
Categories
Media

- Four specialized tools for different comment analysis needs
- No authentication required – uses web scraping
- Context-efficient statistics tool (~200 tokens vs ~25,000 for full data)
- Built-in capacity planning with memory and timeout limits
- Engagement analysis with actual like-count sorting

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name YouTube Comment Downloader MCP Server
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install dependencies with uv venv && source .venv/bin/activate && uv pip install -e ., test with python test_server.py, and run the server with python src/server.py. For MCP clients (e.g., Claude Desktop), add a configuration block using uv as the command pointing to src/server.py. The server exposes four tools: download_youtube_comments, get_comment_stats, search_comments, and get_top_comments_by_likes.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "youtube comment downloader mcp server": {
            "ytcomment_mcp": {
                "command": "uv",
                "args": [
                    "venv",
                    "&&",
                    "source",
                    ".venv/bin/activate"
                ]
            }
        }
    }
}

McpServers

{
    "ytcomment_mcp": {
        "command": "uv",
        "args": [
            "venv",
            "&&",
            "source",
            ".venv/bin/activate"
        ]
    }
}

YouTube Comment Downloader MCP Server

A Model Context Protocol (MCP) server that provides AI systems with the ability to download and analyze YouTube video comments without requiring API keys.

Features

- 4 specialized tools for different comment analysis needs
- No authentication required - uses web scraping
- Context-efficient statistics tool to avoid token bloat
- Built-in capacity planning with memory and timeout limits
- Engagement analysis with actual like-count sorting

MCP Client Configuration

Add this configuration block to your MCP client (e.g., Claude Desktop):

"ytcomment-mcp": {
  "command": "uv",
  "args": [
    "run",
    "--directory",
    "/Users/chad.kunsman/Documents/PythonProject/ytcomment_mcp",
    "src/server.py"
  ]
}

Available Tools

1. download_youtube_comments

Download raw comment data with full details. - Parameters: video_id, limit (1-10000), sort (0=popular, 1=recent) - Returns: Full comment dataset with all metadata - Use case: When you need complete comment data for analysis

2. get_comment_stats

Get statistical analysis without full comment data (context-efficient). - Parameters: video_id, limit, sort - Returns: Statistics + 5 sample comments (~200 tokens vs ~25,000) - Use case: Quick engagement insights without context bloat - Triggers: "how engaged", "what's the engagement", "comment patterns"

3. search_comments

Search for specific terms within comments. - Parameters: video_id, search_term, limit, sort - Returns: Matching comments + search metadata - Use case: Finding mentions, sentiment analysis, topic research - Triggers: "find comments about", "search for", "mentions of"

4. get_top_comments_by_likes

Get most-liked comments sorted by actual like count (not YouTube's "popular"). - Parameters: video_id, top_count (1-100), sample_size (100-2000, default: 500) - Returns: Top comments ranked by likes + engagement stats - Use case: Finding viral comments that YouTube's algorithm might not surface first - Triggers: "most popular", "most liked", "viral comments", "best comments"

Quick Start

```bash

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.