Ytranscript Mcp

io.github.nnnoelPublished by GitHub account nnnoelv0.1.0Updated Oct 25, 2026

YouTube transcripts for AI tools. No proxies needed; transcribes videos without captions.

VerifiedSTDIODesktop onlyWeb Search & ScrapingMedia & Design

Overview

AI-generated overview

Local MCP server that fetches YouTube video transcripts, including AI speech-to-text for videos without captions, for AI assistants to summarize or search.

What you can do
  • Fetch the transcript of a YouTube video from a URL or 11-character video ID
  • Choose a caption language track, or default to the language actually spoken
  • Return plain text or timestamped lines, with an optional character cap and a note on what was cut
  • Report units used and the monthly total with each response
When to use it
Useful when you want an assistant to summarize, quote, timestamp-search or translate YouTube videos, especially videos without captions or when running from cloud hosts where YouTube blocks transcript requests.
Requirements
Runs locally over stdio, typically via npx, so Node.js is needed. Requires a YTRANSCRIPT_API_KEY environment variable from the provider's developer page; a free plan with 50 units a month is offered. Network access to the provider's API is required.
Before you install
The API key is a secret passed in the environment. Usage is metered: caption transcripts cost 1 unit, AI-transcribed videos 15 units, and paid plans or pay-as-you-go packs cost money. Video URLs and IDs are sent to the third-party yTranscript API.

Installation

In SourceWeft

  1. Open Ytranscript Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

ytranscript-mcp

[npm] [ytranscript-mcp MCP server]

An MCP server that gives Claude, Cursor, VS Code, and other AI tools the transcript of any YouTube video.

  • Works from anywhere. Runs fine on AWS, Lambda, Vercel, n8n Cloud, and other cloud hosts. There are no proxies to buy and no IP bans to work around. YouTube blocks most cloud IPs for transcript requests; the yTranscript API handles that for you.
  • Handles videos without captions. If a video has no captions, it's transcribed with AI speech-to-text.
  • Returns the language actually spoken by default, including on auto-dubbed videos. Pass lang to pick a specific caption track.
  • Keeps long videos manageable. Choose plain text or timestamped lines, and cap the length so a two-hour video doesn't flood the model's context.

Setup

  1. Get a free API key at ytranscript.com/developers. The free plan includes 50 units a month, no card required.
  2. Add the server to your client using one of the configs below.

Claude Code

bash
claude mcp add ytranscript -e YTRANSCRIPT_API_KEY=yk_live_your_key -- npx -y ytranscript-mcp

Claude Desktop

Add this to claude_desktop_config.json. Open it from Settings → Developer → Edit Config.

json
{  "mcpServers": {    "ytranscript": {      "command": "npx",      "args": ["-y", "ytranscript-mcp"],      "env": { "YTRANSCRIPT_API_KEY": "yk_live_your_key" }    }  }}

Cursor

Add this to ~/.cursor/mcp.json, or to .cursor/mcp.json in a project:

json
{  "mcpServers": {    "ytranscript": {      "command": "npx",      "args": ["-y", "ytranscript-mcp"],      "env": { "YTRANSCRIPT_API_KEY": "yk_live_your_key" }    }  }}

VS Code

Add this to .vscode/mcp.json:

json
{  "servers": {    "ytranscript": {      "command": "npx",      "args": ["-y", "ytranscript-mcp"],      "env": { "YTRANSCRIPT_API_KEY": "yk_live_your_key" }    }  }}

Any other MCP client that runs stdio servers works the same way: run npx -y ytranscript-mcp with YTRANSCRIPT_API_KEY set.

Tool: get_transcript

ArgumentRequiredDescription
videoyesA YouTube URL (watch, youtu.be, shorts, embed) or an 11-character video ID
langnoLanguage code of the caption track to fetch, such as en or es. Omit it to get the video's original language
formatnotext (default) returns plain text. timestamped returns one line per segment with [m:ss] times
max_charactersnoCut the transcript at about this many characters. The response says how much was left out

Things to ask your assistant:

  • "Summarize this video: https://youtu.be/..."
  • "What does the speaker say about pricing, and at what timestamps?"
  • "Pull the transcript of this Spanish video and translate it to English."

Every response ends with the units used and your monthly total, so you can keep an eye on your quota.

Pricing

A transcript from captions costs 1 unit. A video without captions, transcribed with AI, costs 15 units. Failed requests are free.

PlanPriceUnits per month
Free$050
Starter$9/mo1,000
Developer$29/mo10,000
Scale$79/mo50,000

Need more in a given month? Pay-as-you-go packs add 1,000 units for $10, 5,000 for $40 or 20,000 for $120, on top of any plan. See ytranscript.com/developers for details.

Related

License

MIT

Source: README.md at commit 6bdc462

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestSep 24, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts