Provides AI tools with YouTube video transcripts, including AI-generated speech-to-text for videos without existing captions.
Also known as nnnoel/ytranscript-mcp
- Stars
- 0
- Tools
- 4
- Downloads, 30 days
- —
- Latest version
- 0.3.0
- Last commit
- Nov 14, 2026
- License
- MIT
What is ytranscript MCP?
ytranscript provides AI tools with YouTube video transcripts, including AI-generated speech-to-text for videos without existing captions. It exposes 4 tools, such as video, lang, format.
Summary generated from the project's README
About ytranscript MCP server
Accessing YouTube video content directly through Claude, Cursor, or VS Code is what this MCP server enables for developers and researchers. By using the get_transcript tool, users can retrieve text from any video using a URL or an 11-character video ID. The server works in cloud environments like AWS, Lambda, or Vercel because it utilizes the yTranscript API to bypass IP bans that often block standard cloud requests.
This tool handles both standard caption tracks and videos that lack existing captions by using AI speech-to-text technology. You can request transcripts in specific languages, choose between plain text or timestamped formats, and set a max_characters limit to prevent long videos from exceeding your model's context window. Setup requires a YTRANSCRIPT_API_KEY, with a free tier providing 50 units per month. While standard caption requests cost 1 unit, AI-generated transcriptions for videos without captions cost 15 units.
What you can do with it
- 1Summarize video contentAsk your AI assistant to provide a concise summary of a specific YouTube video link.
- 2Extract specific information with timestampsIdentify exactly when a speaker discusses a particular topic like pricing.
- 3Translate foreign language videosRetrieve the transcript of a video in a different language to translate it into English.
- 4Process videos without captionsGenerate text for videos that do not have any pre-existing caption tracks available.
Written from the project's README. Every use case is checked against a quote from it.
How to install ytranscript MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall ytranscript MCP in Claude Code
$ claude mcp add --env 'YTRANSCRIPT_API_KEY=<YOUR_YTRANSCRIPT_API_KEY>' ytranscript-mcp -- npx -y ytranscript-mcpInstall ytranscript MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"ytranscript-mcp": {
"command": "npx",
"args": [
"-y",
"ytranscript-mcp"
],
"env": {
"YTRANSCRIPT_API_KEY": "<YOUR_YTRANSCRIPT_API_KEY>"
}
}
}
}Install ytranscript MCP in VS Code
.vscode/mcp.json
{
"servers": {
"ytranscript-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"ytranscript-mcp"
],
"env": {
"YTRANSCRIPT_API_KEY": "<YOUR_YTRANSCRIPT_API_KEY>"
}
}
}
}Install ytranscript MCP in VS Code CLI
$ code --add-mcp '{"name":"ytranscript-mcp","type":"stdio","command":"npx","args":["-y","ytranscript-mcp"],"env":{"YTRANSCRIPT_API_KEY":"<YOUR_YTRANSCRIPT_API_KEY>"}}'Install ytranscript MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"ytranscript-mcp": {
"command": "npx",
"args": [
"-y",
"ytranscript-mcp"
],
"env": {
"YTRANSCRIPT_API_KEY": "<YOUR_YTRANSCRIPT_API_KEY>"
}
}
}
}Install ytranscript MCP in Codex
$ codex mcp add ytranscript-mcp --env 'YTRANSCRIPT_API_KEY=<YOUR_YTRANSCRIPT_API_KEY>' -- npx -y ytranscript-mcpInstall ytranscript MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.ytranscript-mcp] command = "npx" args = ["-y", "ytranscript-mcp"] [mcp_servers.ytranscript-mcp.env] YTRANSCRIPT_API_KEY = "<YOUR_YTRANSCRIPT_API_KEY>"
Install ytranscript MCP in Gemini CLI
$ gemini mcp add -s user -e 'YTRANSCRIPT_API_KEY=<YOUR_YTRANSCRIPT_API_KEY>' ytranscript-mcp npx -- -y ytranscript-mcpInstall ytranscript MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"ytranscript-mcp": {
"command": "npx",
"args": [
"-y",
"ytranscript-mcp"
],
"env": {
"YTRANSCRIPT_API_KEY": "<YOUR_YTRANSCRIPT_API_KEY>"
}
}
}
}ytranscript MCP tools 4
Detected from the READMEvideolangformatmax_characters
| video | — | |
| lang | — | |
| format | — | |
| max_characters | — |
Configuration
YTRANSCRIPT_API_KEYRequiredSecretAPI key from https://ytranscript.com/developers (free plan available)
| Name | Description | |
|---|---|---|
| YTRANSCRIPT_API_KEY | API key from https://ytranscript.com/developers (free plan available) | RequiredSecret |
Automated checks
Ran Nov 13, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packagePass
- Remote endpoint uses HTTPSNot checked
- Destructive tools are labelledPass
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesPass
README
View on GitHubytranscript-mcp
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
langto 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
- Get a free API key at ytranscript.com/developers. The free plan includes 50 units a month, no card required.
- Add the server to your client using one of the configs below.
Claude Code
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.
{
"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:
{
"mcpServers": {
"ytranscript": {
"command": "npx",
"args": ["-y", "ytranscript-mcp"],
"env": { "YTRANSCRIPT_API_KEY": "yk_live_your_key" }
}
}
}
VS Code
Add this to .vscode/mcp.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
| Argument | Required | Description |
|---|---|---|
video |
yes | A YouTube URL (watch, youtu.be, shorts, embed) or an 11-character video ID |
lang |
no | Language code of the caption track to fetch, such as en or es. Omit it to get the video's original language |
format |
no | text (default) returns plain text. timestamped returns one line per segment with [m:ss] times |
max_characters |
no | Cut 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.
| Plan | Price | Units per month |
|---|---|---|
| Free | $0 | 50 |
| Starter | $9/mo | 1,000 |
| Developer | $29/mo | 10,000 |
| Scale | $79/mo | 50,000 |
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
ytranscript-apiis the JavaScript/TypeScript client this server is built on.- YouTube Transcript Scraper on Apify runs the same transcripts in bulk, with pay-per-result pricing and no yTranscript account needed.
License
MIT
ytranscript MCP questions
How do I add ytranscript MCP to Claude Code?
Run claude mcp add --env 'YTRANSCRIPT_API_KEY=<YOUR_YTRANSCRIPT_API_KEY>' ytranscript-mcp -- npx -y ytranscript-mcp in your terminal. Add --scope user to make it available in every project.
How do I add ytranscript MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does ytranscript MCP provide?
It exposes 4 tools, including video, lang, format, max_characters.
Can it transcribe videos that don't have captions?
Yes, if a video lacks captions, the server uses AI speech-to-text to transcribe it.
Does it work on cloud hosting platforms?
Yes, it runs on AWS, Lambda, Vercel, n8n Cloud, and other hosts without needing proxies.