YouTube Transcript & Search MCP Server

🎬 Why

Everyone who works with an agent has run this exchange at least once.

You:   Summarize this. https://www.youtube.com/watch?v=kCc8FmEb1nY
Agent: I'm not able to watch videos. If you paste the transcript here, I'll gladly help!

The transcript is precisely the thing the agent cannot get on its own. With this server connected, the same message simply resolves.

You:   Summarize this. https://www.youtube.com/watch?v=kCc8FmEb1nY
Agent: → get_transcript(video="kCc8FmEb1nY", video_metadata=true)      1 credit

       That's "Let's build GPT: from scratch, in code, spelled out" by Andrej
       Karpathy, 1:56:20. He starts from an empty file and a bigram model,
       derives self-attention step by step, and ends with a working GPT that...

Reading one video is rarely where the job ends. Here is how the three ways of getting YouTube data into an agent actually compare.

⚡ Quick start

1. Get an API key. Sign up at transcriptout.com and create a key in the dashboard. New accounts receive 100 free credits and no card is asked. Keys start with sk_ and are shown once.

2. Point your client at the server. It speaks streamable HTTP and authenticates with one Bearer header.

{
  "mcpServers": {
    "transcriptout": {
      "url": "https://api.transcriptout.com/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}

One-click buttons for Cursor and VS Code sit at the top of this page. Exact snippets for the rest live under Install in your client.

3. Paste a link.

Summarize this talk and pull the three strongest quotes.
https://www.youtube.com/watch?v=dQw4w9WgXcQ

The agent picks get_transcript on its own, reads the timed text and answers from it. Every response carries an X-Credits-Remaining header, so the budget stays in view the whole session.

🧰 The 14 tools

All 14 tools are exposed automatically once you connect. Most calls cost 1 credit. Credits are refunded automatically when a call fails before reaching YouTube (validation errors, rate limits, our own capacity), so you pay for answers, not for failures. A definitive "this video has no captions" is an answer and is billed like one.

1. get_transcript · 1 credit

Fetch the transcript of any YouTube video. format=text (default) returns plain readable text, cheapest for a model to reason over, and format=json returns timed segments.

Left out, segment cuts auto-generated tracks into ~180-character segments and returns manual tracks exactly as their author broke them. Pass it whenever you need one size regardless of which track answers.

Example output (format=json):

{
  "video_id": "dQw4w9WgXcQ",
  "language": "en",
  "kind": "manual",
  "transcript": [
    { "text": "Never gonna give you up", "start": 18.0, "duration": 4.12 },
    { "text": "Never gonna let you down", "start": 22.12, "duration": 3.85 }
  ]
}

srt and vtt come back as complete subtitle file bodies, ready to be written to disk by the agent. srv3 is the raw source XML and does not combine with segment.

2. get_video_info · 1 credit

Metadata for one video (title, channel, duration, views, thumbnails) plus the list of available transcript languages, WITHOUT downloading the subtitles.

Credit hygiene: if you are going to fetch the transcript anyway, call get_transcript with video_metadata=true instead. It returns both for one credit where these are two calls and two.

3. search_youtube · 1 credit/page

Search YouTube for videos or channels. Paginate with next_page_token. has_more tells you whether another page exists.

4. list_channel_videos · 1 credit/page

List videos from a channel's Videos tab, newest first. Accepts an @handle, a channel name, a UC... channel ID or a channel URL.

ids_only=true is the cheap way to feed submit_transcripts_job.

5. search_channel_videos · 1 credit/page

Search inside one channel using YouTube's native relevance search. A result whose title lacks the query word is normal. Results are ranked by relevance, not by substring.

6. latest_channel_videos · 1 credit

The ~15 most recent videos of a channel from its RSS feed. The fastest and cheapest way to check what a channel published recently.

7. list_playlist_videos · 1 credit/page

Every video of a playlist in playlist order. Accepts a PL... playlist ID or a URL with list=.

8. search_playlist_videos · 1 credit

Find videos inside a playlist by a substring of the title (case-insensitive). YouTube has no native playlist search, so this scans up to 500 playlist items. truncated=true means there may be more matches beyond the scanned window.

9. submit_transcripts_job · 1 credit per video

Queue transcripts for MANY videos at once (up to 4,000) and get a job_id back immediately. The work continues in the background at your rate limit's pace. Use this instead of calling get_transcript in a loop for more than a handful of videos.

Requires a user key (sk_...). Credits are charged on submit and refunded per video when a video could not be delivered through our fault.

10. get_transcripts_job · free

Progress of a batch job: status (queued/running/done/cancelled), how many videos are ready, failed and pending. Polling a job you already paid for costs nothing.

11. get_transcripts_results · free

Finished transcripts from a batch job, in the order submitted, paged with next_page_token (limit 1-500, default 100). Results appear as they are fetched, so you can read before the job is done. Each entry is exactly what get_transcript returns for that video, plus its status.

12. get_transcripts_result · free

One video's result out of a batch job, by its video id, without paging through the whole result set. A 404 means the job does not exist or this video has not finished yet, so check get_transcripts_job before concluding anything.

13. cancel_transcripts_job · free

Cancel a batch job. Credits are refunded ONLY for videos not started yet. Anything already fetched stays in the results and stays paid for.

14. get_credits · free

The remaining credit balance of the key, with no parameters. The balance also rides in the X-Credits-Remaining header of every response, but headers are invisible to the model, so the number a user actually asks about needs a tool. Handy right before a large batch too, since the batch charges 1 credit per video on submit.

🔌 Install in your client

The server is remote, so every install below is a config entry and nothing more. All of them want the same two values, the URL and the Bearer header from Quick start.

Worth doing once, a standing rule for your client

With this in your client's rules/instructions, pasting a YouTube link is enough and the word "transcript" never has to be typed:

Whenever a YouTube link or video ID appears in my message, call the
transcriptout get_transcript tool first and answer from the transcript,
whether I asked for a summary, a quote, a translation or a question.

One-Click Install:

After installing, open the server settings and add the Authorization header with your key.

Manual configuration (~/.cursor/mcp.json):

{
  "mcpServers": {
    "transcriptout": {
      "url": "https://api.transcriptout.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

claude mcp add --transport http transcriptout https://api.transcriptout.com/mcp \
  --header "Authorization: Bearer YOUR_API_KEY"

Claude's custom connectors authenticate remote servers via OAuth, which TranscriptOut does not offer yet (API keys only). On desktop, use Claude Code (see above), which supports API-key headers. OAuth support is on the roadmap. Watch the changelog.

Or add this to VS Code user settings (settings.json):

"mcp.servers": {
  "transcriptout": {
    "type": "http",
    "url": "https://api.transcriptout.com/mcp",
    "headers": {
      "Authorization": "Bearer YOUR_API_KEY"
    }
  }
}

1. Create a new Agent
2. Under "Actions" or "Tools", add a new MCP Server
3. URL: https://api.transcriptout.com/mcp
4. Auth Type: API Key
5. Paste your API key from the dashboard

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "transcriptout": {
      "serverUrl": "https://api.transcriptout.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

{
  "mcpServers": {
    "transcriptout": {
      "url": "https://api.transcriptout.com/mcp",
      "type": "streamableHttp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

In Zed settings.json:

{
  "context_servers": {
    "transcriptout": {
      "source": "remote",
      "url": "https://api.transcriptout.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

{
  "mcpServers": {
    "transcriptout": {
      "type": "streamable-http",
      "url": "https://api.transcriptout.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

amp mcp add transcriptout https://api.transcriptout.com/mcp --header "Authorization: Bearer YOUR_API_KEY"

In settings.json under augment.advanced:

"augment.advanced": {
  "mcpServers": [
    {
      "name": "transcriptout",
      "url": "https://api.transcriptout.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  ]
}

In .kilocode/mcp.json:

{
  "mcpServers": {
    "transcriptout": {
      "type": "streamable-http",
      "url": "https://api.transcriptout.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

In Settings → Tools → AI Assistant → MCP:

{
  "mcpServers": {
    "transcriptout": {
      "url": "https://api.transcriptout.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

In ~/.gemini/settings.json:

{
  "mcpServers": {
    "transcriptout": {
      "httpUrl": "https://api.transcriptout.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

In ~/.qwen/settings.json:

{
  "mcpServers": {
    "transcriptout": {
      "httpUrl": "https://api.transcriptout.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

{
  "mcpServers": {
    "transcriptout": {
      "serverUrl": "https://api.transcriptout.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

{
  "mcpServers": {
    "transcriptout": {
      "url": "https://api.transcriptout.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

In mcp.json:

{
  "mcpServers": {
    "transcriptout": {
      "url": "https://api.transcriptout.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

In Settings → AI → MCP:

{
  "transcriptout": {
    "url": "https://api.transcriptout.com/mcp",
    "headers": {
      "Authorization": "Bearer YOUR_API_KEY"
    }
  }
}

In Settings → Connectors → Advanced:

{
  "url": "https://api.transcriptout.com/mcp",
  "headers": {
    "Authorization": "Bearer YOUR_API_KEY"
  }
}

🧩 Install as an Agent Plugin

This repository root is a conformant Agent Plugins 1.0.0 package, the portable format supported by ChatGPT, Codex, Cursor, GitHub Copilot, Kiro and VS Code. One install gets you the MCP server and a bundled youtube skill that teaches your agent when to use each tool and how not to waste credits.

plugin.json                # manifest
mcp.json                   # hosted MCP server, streamable-http
skills/youtube/SKILL.md    # when + how to use the 14 tools

VS Code. Command Palette → Chat: Install Plugin From Source, then paste:

https://github.com/artemchuikin/youtube-mcp

Or register a local clone in settings.json:

"chat.pluginLocations": { "/absolute/path/to/youtube-mcp": true }

Cursor. Customize in the sidebar → find the plugin → Install. For a local clone:

git clone https://github.com/artemchuikin/youtube-mcp ~/.cursor/plugins/local/transcriptout

Then Developer: Reload Window.

ChatGPT, Codex, GitHub Copilot, Kiro, any other client. Point your client's plugin mechanism at this repository, or at a local clone. Agent Plugins 1.0.0 standardizes the package format, not installation, so each client owns its own install flow.

There are no credentials in this package, Agent Plugins 1.0.0 forbids embedded secrets. The server authenticates with an API key you add in your client's MCP settings (see Keys and security). Verify the package yourself:

curl -sO https://agent-plugins.org/schemas/1.0.0/plugin.schema.json
curl -sO https://agent-plugins.org/schemas/1.0.0/mcp.schema.json
npx ajv-cli@5 validate --spec=draft2020 -s plugin.schema.json -d plugin.json
npx ajv-cli@5 validate --spec=draft2020 -s mcp.schema.json    -d mcp.json

🔑 Keys and security

• A key is shown once, at creation. Keep it in an environment variable and out of version control.
• A leaked key dies the moment you revoke it in the dashboard. An account holds up to 20 keys, so give every machine its own.
• Prefer to stay in the chat? An agent with the companion youtube-skills installed can open the account and mint the key for you, by email and a 6-digit code, no browser involved.
• There is no OAuth flow yet, so clients whose connectors cannot send a custom header (Claude Desktop and Claude Web) should go through Claude Code for now.

🐳 Run it locally

The hosted endpoint needs no install, but stdio-only clients, sandboxes and container platforms sometimes want a process of their own. The repo carries one: server.js is a complete local MCP server (official SDK, stdio transport) whose 14 tools each make one HTTPS call to the TranscriptOut REST API — the same shape as any SaaS-backed MCP server.

# as a container
docker build -t transcriptout-mcp https://github.com/artemchuikin/youtube-mcp.git
docker run -i -e TRANSCRIPTOUT_API_KEY=sk_your_key transcriptout-mcp

# or straight from a checkout (Node 20+)
npm install && TRANSCRIPTOUT_API_KEY=sk_your_key node server.js

Without a key it still connects and lists all tools; tool calls answer with a clear 401 that says where to get one. Tool definitions ship in tools.json and refresh from the live catalog at startup when the network allows, so the local list never goes stale.

🍳 Recipes

Every prompt below is paste-able as written.

The bulk recipe spelled out. "Archive a whole channel" is four tool calls, not a script:

1. list_channel_videos with ids_only=true: up to 500 video IDs per page
2. submit_transcripts_job with those IDs (up to 4,000, duplicates dropped before billing, idempotency_key makes a retry free)
3. get_transcripts_job until status is done. The job paces itself inside your rate limit
4. get_transcripts_results page by page, readable while the job still runs

Anything the service fails to deliver is refunded per video, so the bill matches the archive.

💳 Pricing and limits

• Subscriptions are a slider from 1,000 to 100,000 credits/month in steps of 1,000, and the per-1,000 rate falls with volume (10,000/mo is $27.49, not $44.90). The annual discount grows with volume, from ~16% to ~35%.
• 1 credit = 1 answered request. Calls that fail before reaching YouTube (validation, rate limit, our capacity) are refunded automatically. The running balance rides in the X-Credits-Remaining header.
• One-time credit packs that never expire can be bought on top of an active subscription.
• View pricing · Manage billing

🧯 When a call fails

• Verify your API key starts with sk_
• Check for extra spaces when copying
• Ensure the key is active in your dashboard
• Revoked keys fail immediately. Issue a new one in the dashboard

• Check your balance in the dashboard
• Subscribe or buy a credit pack at transcriptout.com/billing

• 404: the video has no captions on the requested language/track, or the ID is wrong. This is a definitive answer, retrying won't change it.
• 410: the video was removed.
• 451: age-restricted or members-only content.

• Respect the Retry-After header. Both are refunded automatically
• For bulk work use submit_transcripts_job: it paces itself inside your rate limit instead of bouncing off it

Every error body is {"ok": false, "code": "...", "detail": "...", "request_id": "req_..."}. Branch on the machine-readable code, not on the human text. Include request_id when contacting support.

🌐 Prefer plain REST?

Building an app instead of an agent? The same backend ships as a JSON REST API, with the same five transcript formats plus raw file download (download=true).

Base URL: https://api.transcriptout.com/v1

Client libraries wrap it for Python and Node.js. Both are drop-in replacements for the popular open-source ones, so switching is one import line.

pip install transcriptout   # replaces youtube-transcript-api
npm i transcriptout         # replaces youtube-transcript

Source: youtube-transcript-python · youtube-transcript-js

🔗 Links

• 🌐 Website: transcriptout.com
• 📚 Docs: transcriptout.com/docs
• 🧰 Agent skills (same backend, no MCP required): github.com/artemchuikin/youtube-skills
• 🐍 Python library: github.com/artemchuikin/youtube-transcript-python
• 📦 Node.js library: github.com/artemchuikin/youtube-transcript-js
• 💬 Contact: [email protected]

📇 MCP Registry

This server is published to the official Model Context Protocol Registry under the name:

com.transcriptout/youtube-transcript-and-youtube-search

TranscriptOut is an independent service and is not affiliated with, endorsed by, or sponsored by YouTube or Google LLC. "YouTube" is a trademark of Google LLC.