YouTube Transcripts, Search & Summaries

YouTube Transcripts MCP Server

Hosted version (no setup): apify.com/parallelstudio/youtube-transcripts-mcp. Connect any MCP client to https://parallelstudio--youtube-transcripts-mcp.apify.actor/mcp with your Apify token, pay per call. This repo is the open-source code; you can also run it locally with npm install && npm run build && node dist/index.js (stdio).

Give your AI agent YouTube transcripts, search, chapters and summaries. This MCP server fetches the captions of any public YouTube video (as plain text, timestamped segments or SRT) together with its metadata. It also searches YouTube, returns chapters, and builds structured extractive summaries where every point links to the moment it comes from.

Worked examples: four end-to-end workflows with prompts, tool calls, costs and real output are in docs/workflows.md.

It works with Claude Desktop, Claude Code, Cursor, VS Code, Windsurf and any other client that supports MCP over Streamable HTTP. You don't need a YouTube API key or a Google account. No LLM runs on the server, so you don't pay for anyone else's tokens.

What you can do with it

• Research faster. "Summarize this 2-hour podcast and give me the 10 key points with timestamps."
• Answer questions about a video. Load the transcript and let your agent quote and cite exact moments.
• Navigate long videos. Get the creator's chapters. If the video has none, get topic segments derived from the transcript.
• Find sources. Search YouTube with filters for upload date, length, sort order and "has subtitles", then pull transcripts for the best hits.
• Repurpose content. Export SRT subtitles, build show notes, or draft a blog post from a talk, using any caption language or YouTube's machine translation.

Tools

video accepts an 11-character id (dQw4w9WgXcQ) or any YouTube URL: watch?v=, youtu.be/, /shorts/, /embed/, /live/, m. and music. hosts, and youtube-nocookie.com.

All tools are read-only.

Error codes

Failures come back as MCP tool errors (isError: true). The text starts with Error ( ): … and structuredContent.error holds { code, message, retryable, details }, so your agent can react to the code instead of parsing the message:

Pricing

This Actor uses pay-per-event pricing. Tool events are charged only for successful tool calls. Failed calls are not charged as tool events, whether they fail on validation, because the video is private or has no captions, or because YouTube blocks the request. Apify also charges its standard Actor start event ($0.00005 per GB of memory, minimum one event) each time a server instance starts. At the default 512 MB standby memory that's $0.00005 per start, and one running instance serves many calls before it idles out. The Pricing tab on this Actor is the authoritative list of current prices.

A search that returns zero results is still a successful call and is charged as one search event.

Connect your MCP client

Endpoint (Streamable HTTP):

https://parallelstudio--youtube-transcripts-mcp.apify.actor/mcp

Authenticate with your Apify API token by sending it as Authorization: Bearer .

Cursor (~/.cursor/mcp.json or .cursor/mcp.json)

{

"mcpServers": { "youtube-transcripts": { "url": "https://parallelstudio--youtube-transcripts-mcp.apify.actor/mcp", "headers": { "Authorization": "Bearer " } } } }

Windsurf (~/.codeium/windsurf/mcp_config.json)

{

"mcpServers": { "youtube-transcripts": { "serverUrl": "https://parallelstudio--youtube-transcripts-mcp.apify.actor/mcp", "headers": { "Authorization": "Bearer " } } } }

Claude Desktop (claude_desktop_config.json)

Claude Desktop's config file only launches local (stdio) servers, so bridge to the hosted endpoint with mcp-remote (needs Node.js). The same block works in any other client that only supports stdio:

{

"mcpServers": { "youtube-transcripts": { "command": "npx", "args": [ "-y", "mcp-remote", "https://parallelstudio--youtube-transcripts-mcp.apify.actor/mcp", "--header", "Authorization: Bearer ${APIFY_TOKEN}" ], "env": { "APIFY_TOKEN": " " } } } }

Clients that can't send headers

Apify also accepts the token as a token query parameter, so a client that only takes a URL can use:

https://parallelstudio--youtube-transcripts-mcp.apify.actor/mcp?token=<APIFY_TOKEN>

Prefer the Authorization header when your client supports it: a token in a URL can end up in logs. A scoped Apify token limits the damage if it leaks.

Claude Code

claude mcp add --transport http youtube-transcripts \

https://parallelstudio--youtube-transcripts-mcp.apify.actor/mcp \ --header "Authorization: Bearer $APIFY_TOKEN"

VS Code (.vscode/mcp.json)

{

"servers": { "youtube-transcripts": { "type": "http", "url": "https://parallelstudio--youtube-transcripts-mcp.apify.actor/mcp", "headers": { "Authorization": "Bearer ${input:apifyToken}" } } }, "inputs": [{ "id": "apifyToken", "type": "promptString", "description": "Apify API token", "password": true }] }

Example prompts

• "Get the transcript of https://youtu.be/aircAruvnKk and explain the part about gradient descent, citing timestamps."
• "Search for talks about Rust async from the last year, longer than 20 minutes and with subtitles, then summarize the top 3."
• "Give me the chapters of this 3-hour livestream. If it has none, split it by topic."
• "Export German subtitles for this video as SRT. Translate them if there's no German track."

Four of these, with the exact tool calls, per-call costs and real output from live YouTube videos, are in docs/workflows.md:

Example outputs

The excerpts below come from the bundled fixture videos used in the test suite (see demo/transcript.md for every call and response).

`get_transcript` { "video": "kM3pLz8QwT0", "format": "segments", "include_timestamps": true } (trimmed):

{

"video": { "id": "kM3pLz8QwT0", "url": "https://www.youtube.com/watch?v=kM3pLz8QwT0", "title": "How Solar Panels Actually Work (Explained Simply)", "channel": "Bright Circuits", "durationSeconds": 552, "duration": "9:12", "viewCount": 1843291, "publishDate": "2025-03-14T07:00:12-07:00", "category": "Education", "isLive": false }, "transcript": { "language": "en", "languageName": "English", "autoGenerated": false, "translatedFrom": null, "matchedPreference": true, "format": "segments", "segmentCount": 128, "wordCount": 870, "truncated": false, "segments": [ { "start": 0, "duration": 4.116, "time": "0:00", "text": "Hey everyone, welcome back to Bright Circuits." }, { "start": 4.2, "duration": 4.116, "time": "0:04", "text": "Today we're answering a question I get" } ] }, "availableLanguages": [