AgentStack
MCP unreviewed MIT Self-run

Mcp Youtube Transcript

mcp-sinco-lab-mcp-youtube-transcript · by sinco-lab

TypeScript MCP server for retrieving YouTube transcripts in Claude Desktop, Cursor, Cline, Codex, and other MCP clients

No reviews yet
0 installs
13 views
0.0% view→install

Install

$ agentstack add mcp-sinco-lab-mcp-youtube-transcript

Open-source listing — not yet scanned by AgentStack. Follow the source repository for install instructions.

Security review

⚠ Flagged

1 finding(s); flagged for manual review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures
  • high Destructive filesystem operation.

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Mcp Youtube Transcript? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

MCP YouTube Transcript Server

A TypeScript Model Context Protocol server that retrieves YouTube transcripts for Claude Desktop, Cursor, Cline, Codex, and other MCP-compatible clients. It is designed for local npx usage so transcript requests are made from your own machine instead of a remote proxy.

[](https://www.npmjs.com/package/@sinco-lab/mcp-youtube-transcript) [](https://www.npmjs.com/package/@sinco-lab/mcp-youtube-transcript) [](https://github.com/sinco-lab/mcp-youtube-transcript) [](./LICENSE)

Table of Contents

  • [Features](#features)
  • [Getting Started](#getting-started)
  • [Prerequisites](#prerequisites)
  • [Installation](#installation)
  • [Usage](#usage)
  • [Basic Configuration](#basic-configuration)
  • [Docker](#docker)
  • [Testing](#testing)
  • [Troubleshooting and Maintenance](#troubleshooting-and-maintenance)
  • [Tools](#tools)
  • [Development](#development)
  • [Contributing](#contributing)
  • [License](#license)

Features

Key capabilities:

  • Extract transcripts from YouTube videos
  • Support for multiple languages
  • Android InnerTube fallback for current YouTube caption responses
  • Compatible tool names: get_transcripts and get_transcript
  • Timestamped transcript output with get_timed_transcript
  • Video metadata and available transcript languages
  • Format text with continuous or paragraph mode
  • Retrieve video titles and metadata
  • Automatic paragraph segmentation
  • Text normalization and HTML entity decoding
  • Robust error handling
  • Timestamp and overlap detection

Getting Started

Prerequisites

  • Node.js 18 or higher

Installation

Use a local npx configuration so transcript requests are sent from your own machine instead of a remote MCP proxy.

  1. Create or edit the Claude Desktop configuration file:
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  1. Add the following configuration:
{
  "mcpServers": {
    "youtube-transcript": {
      "command": "npx",
      "args": [
        "-y",
        "@sinco-lab/mcp-youtube-transcript"
      ]
    }
  }
}

Quick setup script for macOS:

# Create directory if it doesn't exist
mkdir -p ~/Library/Application\ Support/Claude

# Create or update config file
cat > ~/Library/Application\ Support/Claude/claude_desktop_config.json  **Note**: Claude app automatically prefixes MCP server log files with `mcp-server-`. For example, our server's logs will be written to `mcp-server-youtube-transcript.log`.

#### Cleaning the `npx` Cache

If you encounter issues related to the `npx` cache, you can manually clean it using:

```bash
rm -rf ~/.npm/_npx

This will remove the cached packages and allow you to start fresh.

Tools

get_transcripts

Fetches transcript text from a YouTube video.

Parameters:

  • url (string, required): YouTube video URL or ID
  • lang (string, optional): Language code. If omitted, the best available caption track is used.
  • enableParagraphs (boolean, optional): Enable paragraph mode. Default: false.

get_transcript

Alias of get_transcripts for compatibility with other YouTube transcript MCP servers.

gettimedtranscript

Fetches transcript text with one timestamped line per caption segment.

Parameters:

  • url (string, required): YouTube video URL or ID
  • lang (string, optional): Language code. If omitted, the best available caption track is used.

Example output:

[00:00:01.250] Hello and welcome
[00:00:03.500] Today we are going to...

getvideoinfo

Fetches basic video metadata and available transcript languages without returning the full transcript.

Parameters:

  • url (string, required): YouTube video URL or ID

getavailablelanguages

Lists available transcript languages for a YouTube video. Use this before retrying with a specific lang value.

Parameters:

  • url (string, required): YouTube video URL or ID

Development

Project Structure

├── src/
│ ├── index.ts            # Server entry point
│ ├── youtube.ts          # YouTube transcript fetching logic
├── tests/                # Node test runner coverage
├── docs/                 # Maintenance notes
├── Dockerfile            # Local container build
├── dist/                 # Compiled output
└── package.json

Key Components

  • YouTubeTranscriptFetcher: Core transcript fetching functionality
  • YouTubeUtils: Text processing and utilities

Features and Capabilities

  • Error Handling:
  • Invalid URLs/IDs
  • Unavailable transcripts
  • Language availability
  • Network errors
  • Rate limiting
  • Empty caption responses caused by YouTube client enforcement
  • Text Processing:
  • HTML entity decoding
  • Punctuation normalization
  • Space normalization
  • srv3, classic XML, json3, and VTT caption parsing
  • Smart paragraph detection

YouTube Access Notes

YouTube does not provide an official public API for downloading captions from arbitrary videos. This server uses YouTube's internal caption data exposed to web and Android clients. YouTube may still reject requests from some networks, hosted environments, or remote MCP providers. When that happens, the server now returns a more specific diagnostic instead of a generic No transcripts found error.

Contributing

We welcome contributions! Please feel free to submit issues and pull requests.

License

This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.

Related Projects

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.