youtube-transcripts

## What it does Gives any MCP-compatible agent (Claude, Cursor, VS Code, ChatGPT, Codex) clean YouTube transcripts as timestamped markdown, ready to use as context. No scraping, no proxies, no YouTube rate limits to manage: the server handles the fetch and caches every result. ## Tools | Tool | What it does | Cost | |---|---|---| | `get_transcript` | Full transcript of one video (ID or URL) | 1 credit | | `get_channel_transcripts` | Recent videos from a channel, newest first (limit 1-50) | 1 credit per video | | `get_playlist_transcripts` | Videos from a playlist, in order (limit 1-50) | 1 credit per video | | `polish_transcript` | Cleaned auto-captions: punctuation restored, filler removed, faithful to what was said | ~3 credits per 1,000 words (min 5) | All tools are read-only. Videos without captions fail free. Rate limit: 5 requests per 10 seconds. ## Setup Get a free API key (25 free credits, no card) at [youtubetranscriptdownload.com/account](https://youtubetranscriptdownload.com/account), then add the server: ```json { "mcpServers": { "ytd": { "url": "https://youtubetranscriptdownload.com/api/mcp", "headers": { "Authorization": "Bearer ytd_sk_YOUR_KEY" } } } } ``` Claude Code: ```bash claude mcp add --transport http \ --header "Authorization: Bearer ytd_sk_YOUR_KEY" \ ytd https://youtubetranscriptdownload.com/api/mcp ``` ## Example output `get_transcript` returns the video title, source link, timestamped text, and a credit footer: ```text How Transformers Work Source: https://youtube.com/watch?v=... [00:00:12] The transformer architecture was introduced in the 2017 paper Attention Is All You Need by Vaswani et al. ... --- 1 credit used · 42 remaining ``` `get_channel_transcripts` and `get_playlist_transcripts` return one section per video, separated by dividers; videos without captions are noted and cost nothing: ```text Lex Fridman Podcast · 3 videos [transcript of video 1] --- [transcript of video 2] --- abc123xyz: No transcript available (skipped, not charged) --- 2 credits used · 40 remaining ``` `polish_transcript` turns raw auto-captions into clean text, faithful to what was said: ```text Before: so um the transformer architecture was introduced uh in the attention is all you need paper in in 2017 After: The transformer architecture was introduced in the Attention Is All You Need paper in 2017. ``` ## Links - Setup guide for all clients: https://youtubetranscriptdownload.com/mcp - REST API docs (same backend): https://youtubetranscriptdownload.com/youtube-transcript-api - Pricing: https://youtubetranscriptdownload.com/pricing

Readiness is how fully this listing follows its protocol and how it behaved in our probes over 30 days. It is shown for reference and does not move it in search. Search order and leaderboards use the separate quality grade (here B, 78.8/100), which weighs availability, conformance, p95 speed and descriptor. How the two differ

Compared with peers

Against 53,039 reachable MCP servers in our daily snapshot (2026-11-12 06:46 UTC). Display only; it does not change search order.

Readiness

Higher than 95% of peers

This listing 88 · peer median 81

Latency

Faster than 32% of peers

This listing 484 ms · peer median 326 ms

How many agent tools actually work · All statistics

Listed in

Directories this entry was found in.

How to connect

https://server.smithery.ai/hello-ympt/youtube-transcripts/mcp

curl -X POST https://server.smithery.ai/hello-ympt/youtube-transcripts/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{}}'