YouTube Transcript MCP Server
Fetches transcripts from YouTube videos by video ID with support for multiple languages and configurable language preferences.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@YouTube Transcript MCP Serversummarize the video dQw4w9WgXcQ"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
YouTube Transcript MCP Server
A Model Context Protocol (MCP) server that provides YouTube transcript fetching functionality. This server allows AI assistants to retrieve transcripts from YouTube videos.
Features
Fetch transcripts from YouTube videos using video ID
Support for multiple languages with configurable preferences
Simple MCP tool interface for easy integration
Related MCP server: Personal MCP Server
Installation
Prerequisites
Python 3.8 or higher
uv package manager (recommended) or pip
Install with uv (recommended)
# Clone the repository
git clone https://github.com/arrrggghhh/youtube-transcript-mcp.git
cd youtube-transcript-mcp
# Install dependencies
uv syncConfiguration
Environment Variables
YOUTUBE_TRANSCRIPT_FETCHER_LANGS: Comma-separated list of language codes for transcript preferences (default: "ko,en")Example:
YOUTUBE_TRANSCRIPT_FETCHER_LANGS=en,es,fr,deThe server will attempt to fetch transcripts in the order specified
Adding to Claude Desktop
To use this MCP server with Claude Desktop, you need to add it to your configuration:
1. Locate your Claude Desktop configuration file
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.jsonLinux:
~/.config/Claude/claude_desktop_config.json
2. Edit the configuration file
Add the YouTube Transcript MCP server to the mcpServers section:
{
"mcpServers": {
"youtube-transcript-mcp": {
"command": "/path/to/uv",
"args": [
"run",
"--directory",
"/path/to/cloned/directory",
"--with",
"mcp[cli]",
"--with",
"youtube_transcript_api",
"mcp",
"run",
"/path/to/youtube-transcript-mcp.py"
]
}
}
}Important: Replace /path/to/uv with the actual path to your uv executable, and /path/to/youtube-transcript-mcp.py with the actual path to the youtube-transcript-mcp.py file in your cloned repository.
3. Restart Claude Desktop
After saving the configuration file, restart Claude Desktop for the changes to take effect.
Usage
Once the MCP server is added, you can use it in Claude Desktop by asking Claude to analyze YouTube videos:
"Summarize the YouTube video dQw4w9WgXcQ"
"What are the key points from https://www.youtube.com/watch?v=dQw4w9WgXcQ"
"Give me a brief overview of the content in video ID dQw4w9WgXcQ"The server will automatically extract the video ID, fetch the transcript in the configured languages, and Claude will analyze and summarize the content.
Development
Project Structure
youtube-transcript-mcp/
├── youtube-transcript-mcp.py # Main MCP server
├── transcript_fetcher.py # Core transcript fetching logic
├── pyproject.toml # Project configuration
├── uv.lock # Dependency lock file
└── README.md # This fileAvailable Tools
1 toolget_transcriptD
| Name | Required | Description | Default |
|---|---|---|---|
| video_id | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
1 tool update
- First observed
get_transcript
TDQS
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined as retrieving transcripts, leaving no room for misselection.
The single tool name follows a clear verb_noun pattern (get_transcript), and since there is only one tool, consistency is inherently perfect with no deviations to assess.
A single tool is too few for a server focused on YouTube transcripts, as it lacks essential operations like searching, listing, or managing transcripts. This minimal scope will likely cause agent failures due to incomplete functionality.
The tool set is severely incomplete for the domain of YouTube transcripts. It only provides retrieval (get_transcript) with no support for operations like search, list, update, or delete, creating significant gaps that will hinder agent workflows.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Search YouTube, read video metadata, and fetch transcripts with language preferences
1YouTube transcripts, search, channels, playlists and bulk transcript jobs for AI agents. 14 tools.
YouTube transcripts, search, channel/playlist listings and upload tracking for AI agents. No signup.
Fetch transcripts, subtitles, chapters, metadata and frames from YouTube and 10+ video platforms
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI models like Claude to easily access and utilize subtitle data from YouTube videos by extracting transcripts from video URLs with support for multiple languages.1MIT
- FlicenseNot gradedqualityNot gradedmaintenanceEnables AI assistants to fetch and process YouTube video transcripts in multiple formats and languages, with built-in caching and rate limiting for efficient video content analysis.-
- AlicenseBqualityFmaintenanceEnables AI assistants to analyze and summarize YouTube videos by extracting captions, subtitles, and comprehensive metadata including title, description, and duration in multiple languages.14560MIT
- AlicenseAqualityDmaintenanceEnables AI assistants to fetch YouTube video transcripts with precise timestamps, multi-language support, and time-range filtering.31MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/arrrggghhh/youtube-transcript-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server