YouTube Transcripts MCP server
Commit Oct 8, 2026Extract plain text and timestamped segments from any YouTube video, channel, or playlist for AI analysis.
Also known as retracn/youtube-transcript-api, youtube-transcript-api
- Stars
- 0
- Tools
- 5
- Downloads, 30 days
- —
- Latest version
- 1.0.0
- Last commit
- Oct 8, 2026
- License
- MIT
What is YouTube Transcripts MCP?
YouTube Transcripts extracts plain text and timestamped segments from any YouTube video, channel, or playlist for AI analysis. It exposes 5 tools, such as get-actor-run, get-dataset-items, get-key-value-store-record.
Summary generated from the project's README
About YouTube Transcripts MCP server
Extracting text from YouTube videos for AI analysis is the primary function of this tool. It retrieves transcripts as plain text or timestamped segments from videos, Shorts, channels, or playlists. Users can access manual captions or auto-generated ones in various languages, along with metadata like video title, channel name, view count, and duration.
Developers can connect this service to AI clients like Claude, ChatGPT, or Cursor using a remote MCP URL or a local configuration via npx. Accessing the data requires an Apify account and an API token. The service operates on a usage-based model, costing $1.50 per 1,000 transcripts, though videos that lack available captions do not incur a charge.
This tool differs from the official YouTube Data API because it can retrieve public captions for any video rather than just those owned by the user. It also supports automated workflows, allowing for scheduled runs to transcribe new uploads from a specific channel or playlist automatically.
What you can do with it
- 1Analyze video content via textProvide an AI client with a YouTube URL to get a full transcript for summarization or questioning.
- 2Monitor new channel uploadsSet up a scheduled task to automatically transcribe every new video posted to a specific YouTube channel.
- 3Extract metadata and captionsRetrieve detailed information including video duration, tags, and descriptions alongside the transcript text.
Written from the project's README. Every use case is checked against a quote from it.
How to install YouTube Transcripts MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall YouTube Transcripts MCP in Claude Code
$ claude mcp add --transport http youtube-transcript-api 'https://mcp.apify.com/?tools=automationnation/youtube-transcript-scraper'Install YouTube Transcripts MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"youtube-transcript-api": {
"url": "https://mcp.apify.com/?tools=automationnation/youtube-transcript-scraper"
}
}
}Install YouTube Transcripts MCP in VS Code
.vscode/mcp.json
{
"servers": {
"youtube-transcript-api": {
"type": "http",
"url": "https://mcp.apify.com/?tools=automationnation/youtube-transcript-scraper"
}
}
}Install YouTube Transcripts MCP in VS Code CLI
$ code --add-mcp '{"name":"youtube-transcript-api","type":"http","url":"https://mcp.apify.com/?tools=automationnation/youtube-transcript-scraper"}'Install YouTube Transcripts MCP in Codex
$ codex mcp add youtube-transcript-api --url 'https://mcp.apify.com/?tools=automationnation/youtube-transcript-scraper'Install YouTube Transcripts MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.youtube-transcript-api] url = "https://mcp.apify.com/?tools=automationnation/youtube-transcript-scraper"
Install YouTube Transcripts MCP in Gemini CLI
$ gemini mcp add -s user --transport http youtube-transcript-api 'https://mcp.apify.com/?tools=automationnation/youtube-transcript-scraper'Install YouTube Transcripts MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"youtube-transcript-api": {
"url": "https://mcp.apify.com/?tools=automationnation/youtube-transcript-scraper",
"type": "http"
}
}
}YouTube Transcripts MCP tools 5
Read from the server with tools/listget-actor-runRead-onlyGet detailed information about a specific Actor run. Returns run result: status, storages (datasets/keyValueStores alias map), stats, summary, nextStep. - summary describes the past (e.g. "SUCCEEDED in 22s. 47 items; 3 fields available."). - nextStep prescribes one primary follow-up action with identifiers interpolated (e.g. "Use get-dataset-items with datasetId=..."). - waitSecs (0–45, default 30) waits up to that many seconds for terminal status before returning. USAGE: - Use to check the status of a run started by any Actor-running tool. - Pass waitSecs > 0 to block until terminal (or until the cap elapses). USAGE EXAMPLES: - user_input: Show details of run y2h7sK3Wc - user_input: Wait for run y2h7sK3Wc to finish
get-dataset-itemsRead-onlyGet items (rows) from a dataset — the output/results produced by an Actor run. Returns the rows themselves, not dataset metadata, counts, or a schema. When the user provides a datasetId and asks to retrieve results, output, data, or rows, call this tool directly. Default limit is 20. Use clean=true to skip empty items and hidden fields. USAGE: - Use when you need to read data from a dataset (all items or only selected fields). USAGE EXAMPLES: - user_input: Retrieve results from dataset abc123 - user_input: Get only metadata.url and title from dataset username~my-dataset
get-key-value-store-recordRead-onlyGet the value stored under a specific key in a key-value store — a single record, not a listing of all keys. Requires the exact key name. The response preserves the original Content-Encoding; most clients handle decompression automatically. A record over 262144 bytes is returned as a link to download it, not as its value. USAGE: - Use when you need to retrieve a specific record (JSON, text, or binary) from a store. USAGE EXAMPLES: - user_input: Get record INPUT from store abc123 - user_input: Get record data.json from store username~my-store
abort-actor-runActionAbort an Actor run that is currently starting or running. For runs with status SUCCEEDED, FAILED, ABORTING, ABORTED, or TIMED-OUT, this call has no effect. The results will include the updated run details after the abort request. USAGE: - Use when you need to stop a run that is taking too long or misconfigured. USAGE EXAMPLES: - user_input: Abort run y2h7sK3Wc - user_input: Gracefully abort run y2h7sK3Wc
automationnation--youtube-transcript-scraperActionThis tool calls the Actor "automationnation/youtube-transcript-scraper" and retrieves its output results. Actor description: Get the transcript of any YouTube video, or every video on a channel or playlist: full text and timestamped segments in any caption language or translated, plus title, channel, views and duration. Only-new mode transcribes each new upload once. $1.50 per 1,000 transcripts.
| get-actor-run | Get detailed information about a specific Actor run. Returns run result: status, storages (datasets/keyValueStores alias map), stats, summary, nextStep. - summary describes the past (e.g. "SUCCEEDED in 22s. 47 items; 3 fields available."). - nextStep prescribes one primary follow-up action with identifiers interpolated (e.g. "Use get-dataset-items with datasetId=..."). - waitSecs (0–45, default 30) waits up to that many seconds for terminal status before returning. USAGE: - Use to check the status of a run started by any Actor-running tool. - Pass waitSecs > 0 to block until terminal (or until the cap elapses). USAGE EXAMPLES: - user_input: Show details of run y2h7sK3Wc - user_input: Wait for run y2h7sK3Wc to finish | Read-only |
| get-dataset-items | Get items (rows) from a dataset — the output/results produced by an Actor run. Returns the rows themselves, not dataset metadata, counts, or a schema. When the user provides a datasetId and asks to retrieve results, output, data, or rows, call this tool directly. Default limit is 20. Use clean=true to skip empty items and hidden fields. USAGE: - Use when you need to read data from a dataset (all items or only selected fields). USAGE EXAMPLES: - user_input: Retrieve results from dataset abc123 - user_input: Get only metadata.url and title from dataset username~my-dataset | Read-only |
| get-key-value-store-record | Get the value stored under a specific key in a key-value store — a single record, not a listing of all keys. Requires the exact key name. The response preserves the original Content-Encoding; most clients handle decompression automatically. A record over 262144 bytes is returned as a link to download it, not as its value. USAGE: - Use when you need to retrieve a specific record (JSON, text, or binary) from a store. USAGE EXAMPLES: - user_input: Get record INPUT from store abc123 - user_input: Get record data.json from store username~my-store | Read-only |
| abort-actor-run | Abort an Actor run that is currently starting or running. For runs with status SUCCEEDED, FAILED, ABORTING, ABORTED, or TIMED-OUT, this call has no effect. The results will include the updated run details after the abort request. USAGE: - Use when you need to stop a run that is taking too long or misconfigured. USAGE EXAMPLES: - user_input: Abort run y2h7sK3Wc - user_input: Gracefully abort run y2h7sK3Wc | Action |
| automationnation--youtube-transcript-scraper | This tool calls the Actor "automationnation/youtube-transcript-scraper" and retrieves its output results. Actor description: Get the transcript of any YouTube video, or every video on a channel or playlist: full text and timestamped segments in any caption language or translated, plus title, channel, views and duration. Only-new mode transcribes each new upload once. $1.50 per 1,000 transcripts. | Action |
Configuration
APIFY_TOKEN
| Name | Description | |
|---|---|---|
| APIFY_TOKEN | — |
Automated checks
Ran Nov 16, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableretracn/youtube-transcript-api is public and reachablegithub.com/retracn/youtube-transcript-api ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-08github.com/retracn/youtube-transcript-api ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model5 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-11-25 in 1135 ms; tools/list returned 5 tools (HostedMCP test account)Pass
README
View on GitHubYouTube Transcript Scraper & API: captions and subtitles
YouTube Transcript Scraper is an Apify Actor that returns the transcript of any YouTube video as plain text and timestamped segments, in any caption language, with the title, channel, views and duration. It accepts video, Shorts, channel and playlist URLs, costs $1.50 per 1,000 transcripts and charges nothing for videos without captions.
Price: $1.50 per 1,000 transcripts ($1.20 on Gold and above) · Run it: https://apify.com/automationnation/youtube-transcript-scraper · Guide: https://retracn.github.io/automationnation-actors/youtube-transcript-scraper/
Quick facts
- One row per video: transcript text, timestamped segments, language, auto-generated flag, all caption languages, title, channel, views, duration, description and tags.
- Using youtube-transcript-api? The open-source youtube-transcript-cloud package (github.com/retracn/youtube-transcript-cloud) keeps its interface and runs on this Actor, so it works from AWS, GCP and other servers without RequestBlocked errors.
- Videos, Shorts, channels and playlists (latest 15 videos).
- Manual captions first, then auto-generated; best-effort translation.
- Price: $1.50 per 1,000 transcripts; videos without captions are free.
- Channels on autopilot: with Only new videos on, a scheduled run transcribes each new upload from a channel or playlist once. Guide: https://retracn.github.io/automationnation-actors/guides/auto-transcribe-youtube-channel/
- Node.js on Vercel, Lambda or Render? The open-source youtube-transcript-cloud package (github.com/retracn/youtube-transcript-cloud-js) keeps the youtube-transcript npm API and errors and runs on this Actor, so transcripts work in production.
Example input
{
"videos": [
"https://www.youtube.com/watch?v=UF8uR6Z6KLc"
],
"language": "en"
}
Run it from code
REST API
curl -X POST "https://api.apify.com/v2/acts/automationnation~youtube-transcript-scraper/run-sync-get-dataset-items?token=$APIFY_TOKEN" \
-H "Content-Type: application/json" \
-d '{"videos": ["https://www.youtube.com/watch?v=UF8uR6Z6KLc"], "language": "en"}'
Python — see examples/python_example.py
# pip install apify-client
from apify_client import ApifyClient
client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("automationnation/youtube-transcript-scraper").call(run_input={
"videos": [
"https://www.youtube.com/watch?v=UF8uR6Z6KLc"
],
"language": "en"
})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
print(item.get("title"), item.get("channel"), item.get("wordCount"), item.get("transcriptLanguage"))
JavaScript — see examples/node_example.mjs
// npm install apify-client
import { ApifyClient } from 'apify-client';
const client = new ApifyClient({ token: 'YOUR_APIFY_TOKEN' });
const run = await client.actor('automationnation/youtube-transcript-scraper').call({
"videos": [
"https://www.youtube.com/watch?v=UF8uR6Z6KLc"
],
"language": "en"
});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
for (const item of items) console.log(item.title, item.channel, item.wordCount, item.transcriptLanguage);
Use it with AI agents (MCP)
Hosted MCP server URL (Claude, ChatGPT, Cursor and other clients with remote MCP support):
https://mcp.apify.com?tools=automationnation/youtube-transcript-scraper
Local config for Claude Desktop / Cursor — mcp/claude_desktop_config.json:
{
"mcpServers": {
"youtube-transcript-scraper": {
"command": "npx",
"args": [
"-y",
"@apify/actors-mcp-server",
"--tools",
"automationnation/youtube-transcript-scraper"
],
"env": {
"APIFY_TOKEN": "YOUR_APIFY_TOKEN"
}
}
}
}
FAQ
Is there an official YouTube transcript API? The YouTube Data API only downloads captions for videos you own. YouTube Transcript Scraper returns public captions of any video.
Does it transcribe audio? No, it returns captions YouTube already has (manual or auto-generated); videos without captions come back as no_transcript and aren't charged.
Can it transcribe every new video from a channel automatically? Yes. Add the channel URL, turn on Only new videos and schedule it daily: each run transcribes only new uploads, and videos without captions yet are tried again next time.
More from AutomationNation
- AI Visibility Tracker — $0.05 per answer checked ($0.04 on Gold) + $0.50 per optional report · GitHub examples
- Google Jobs Scraper — $2 per 1,000 jobs ($1.50 on paid plans) + $0.03 per search · GitHub examples
- Google Shopping Scraper — $1 per 1,000 products ($0.80 on Gold and above) · GitHub examples
- Google Flights Scraper — $0.20 per 1,000 flights ($0.16 on Gold and above) · GitHub examples
- Google Hotels Scraper — $1 per 1,000 hotels ($0.80 on Gold and above) · GitHub examples
- Google Ads Transparency Scraper — $1 per 1,000 ads ($0.80 on Gold and above) · GitHub examples
- Google News Scraper — $1 per 1,000 articles ($0.80 on Gold and above) · GitHub examples
- Google Images Scraper — $0.25 per 1,000 images ($0.20 on Gold and above) · GitHub examples
- Google Custom Search API Alternative — $5 per 1,000 searches of up to 10 results ($4 on Gold and above) · GitHub examples
- Google Videos Scraper — $1 per 1,000 videos ($0.80 on Gold and above) · GitHub examples
- Google Trends Scraper — $1 per 1,000 keyword reports ($0.27–$0.90 on paid plans) · $0.50 per 1,000 trending searches · GitHub examples
- App Store Reviews Scraper — $0.08 per 1,000 reviews ($0.05–$0.07 on paid plans) · GitHub examples
- Google Play Reviews Scraper — $0.08 per 1,000 reviews ($0.05–$0.07 on paid plans) · GitHub examples
- AEO & GEO Tracker — Google AI Overview Citation Checker — $0.04 per keyword ($0.032 on Gold), plus $2 per run from 17 Nov 2026; $0.01 per keyword until 16 Oct 2026 · GitHub examples
- Google Maps Leads Scraper — $0.03 per lead ($0.024 on Gold); $0.08 per business found with the no-website or unclaimed filters · GitHub examples
- Google Maps Leads Scraper UK — $0.05 per lead ($0.04 on Gold) · GitHub examples
- App Store & Google Play Reviews Scraper + AI — $0.05 per app report ($0.04 on Gold) · GitHub examples
- UK Companies House Leads — Filing Signals & AI Outreach — $0.008 per lead
- Contact Waterfall Enrichment — Emails & Directors — $0.015 per company
- All Actors and guides · AI visibility trackers compared · Google Jobs scrapers compared · Google Trends scrapers compared · App Store review scrapers compared · Google Play review scrapers compared · YouTube transcript scrapers compared · Google Flights scrapers compared · Google Hotels scrapers compared · Google Ads Transparency scrapers compared · Google Shopping scrapers compared · Google News scrapers compared
This repository holds usage examples. The scraper itself runs on the Apify platform; you need a free Apify account and API token. Examples are MIT licensed.
YouTube Transcripts MCP questions
How do I add YouTube Transcripts MCP to Claude Code?
Run claude mcp add --transport http youtube-transcript-api 'https://mcp.apify.com/?tools=automationnation/youtube-transcript-scraper' in your terminal. Add --scope user to make it available in every project.
How do I add YouTube Transcripts 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 YouTube Transcripts MCP provide?
It exposes 5 tools, including get-actor-run, get-dataset-items, get-key-value-store-record, abort-actor-run, automationnation--youtube-transcript-scraper.
Is there an official YouTube transcript API?
The YouTube Data API only allows downloading captions for videos you own, whereas this scraper returns public captions for any video.
Does it transcribe audio?
No, it retrieves existing manual or auto-generated captions from YouTube.
Can it transcribe every new video from a channel automatically?
Yes, by adding a channel URL and enabling the 'Only new videos' setting with a scheduled run.