YouTube Transcript AI
REMOTE · YOUTUBE-TRANSCRIPT.AI
Read YouTube transcripts and search what people say across 425k videos. Free API key.
Available components
Last scanned (2 hours ago)
Scores higher than 79% of remote servers
Reachable. Last reached 5 Nov 2026.
Category Entertainment and Games
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 12 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability67
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 2229 tokens (~185/item across 12 items; 12 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 1 Nov 26 0
- Tool “list_channel_videos” rewrote its description, which is the text the model reads security
- Server version: 1.3.0 → 1.4.0 functional
- New tool “get_account_status” functional
- “list_channel_videos” added an optional parameter “offset” cosmetic
- 29 Oct 26 −1
- The server rewrote its instructions, which are the text every model session reads security
- Schema quality: 164 → 188 ▼ functional
- Server version: 1.2.0 → 1.3.0 functional
- New tool “get_spoken_context” functional
- New tool “rank_channels_by_topic” functional
- New tool “rank_videos_by_topic” functional
- New tool “search_spoken_words” functional
- New tool “spoken_mentions_over_time” functional
- 28 Oct 26 −2
- The server rewrote its instructions, which are the text every model session reads security
- Schema quality: 211 → 164 ▲ functional
- Server version: 1.1.0 → 1.2.0 functional
- New tool “find_in_transcript” functional
- New tool “get_transcripts_batch” functional
- New tool “get_video_comments” functional
- New tool “list_channel_videos” functional
- New tool “search_youtube_videos” functional
- 14 Oct 26 0
- Server version: 1.0.0 → 1.1.0 functional
- 13 Oct 26 −1
- Tool “get_youtube_transcript” rewrote its description, which is the text the model reads security
- Schema quality: pass → fail ▼ functional
- “get_youtube_transcript” added an optional parameter “offset” cosmetic
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 24 Sept 26 0
- Stability: 0.97 → pass security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Probed https://youtube-transcript.ai/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=youtube-transcript.ai | CN=WE1,O=Google Trust Services,C=US | 4 Oct 2026 | 2 Jan 2027 | ECDSA 256 | ECDSA-SHA256 | 4f41a46fd83a3b1e0e7225325cf89eb8 |
| SANs: youtube-transcript.ai, www.youtube-transcript.ai | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of youtube-transcript.ai. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | present | 1814, 3799 | 8, 8 | Verified |
| youtube-transcript.ai. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=15552000 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://youtube-transcript.ai/mcp | Verified | 200 | |
| http (plaintext) | http://youtube-transcript.ai/mcp | HTTPS enforced | 301 | https://youtube-transcript.ai/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
find_in_transcript ~198
Find where a video talks about something. Give one or more keywords and get back only the matching passages, each with a timestamp and a link that opens the video at that moment. Far cheaper than reading the whole transcript when you are looking for specific points. Matching is a case-insensitive text match, so try synonyms and spelling variants (auto-captions often mis-hear names).
| Name | Type | Req | Description |
|---|---|---|---|
| context | integer | – | Paragraphs (about 30 seconds each) to include before and after each match. Default 1. |
| keywords | array | yes | Words or short phrases to look for (up to 8). A passage matches if it contains any of them. |
| lang | string | – | Optional BCP-47 caption language code. Omit for the default track. |
| max_hits | integer | – | Maximum passages to return. Default 8. |
| video | string | yes | YouTube video URL or 11-character video ID |
No output schema declared.
No examples provided.
get_account_status ~76
Show the plan of the API key on this connection (Free or Pro), the daily request quota, how many requests were used today, how many remain, when the quota resets, and the per-call limits of the tools. Free: it does not use any quota. Call it before a large job to check the quota is enough.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_spoken_context ~121
Read what was said around a moment in a video: the sentences before and after a timestamp. Use it after search_spoken_words to see what a matching sentence was part of, before you quote or rely on it. Works for videos in the library only.
| Name | Type | Req | Description |
|---|---|---|---|
| seconds | number | yes | The moment to read around, in seconds from the start of the video. |
| video | string | yes | YouTube video ID or URL, as returned by search_spoken_words. |
| window | integer | – | Seconds to include before and after. Default 20. |
No output schema declared.
No examples provided.
get_transcripts_batch ~138
Read the transcripts of several videos in one call (up to 5), each cut to a length you choose, so you can skim a set of search results without filling your context. Each video counts as one request against your daily quota. For the rest of a long video use find_in_transcript or get_youtube_transcript.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | Optional BCP-47 caption language code applied to every video. |
| max_chars_each | integer | – | Characters of transcript to keep per video. Default 6000. |
| videos | array | yes | YouTube URLs or 11-character video IDs (up to 5). |
No output schema declared.
No examples provided.
get_video_comments ~88
Fetch the top comments of a YouTube video (YouTube's "top" ordering, replies not included), with like counts. Comments are where viewers report what worked for them, which makes them useful for checking claims made in the video.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | How many comments. Default 30. |
| video | string | yes | YouTube video URL or 11-character video ID |
No output schema declared.
No examples provided.
get_youtube_transcript ~211
Fetch the full text transcript of a YouTube video. Accepts a YouTube URL (watch, youtu.be, shorts, embed) or a bare 11-character video ID, and returns the transcript as plain text with title and metadata. Optionally pass a BCP-47 language code to select a specific caption track. Very long transcripts (multi-hour videos) come back in parts of up to 120,000 characters: when there is more, the result ends with a note giving the offset to pass on the next call.
| Name | Type | Req | Description |
|---|---|---|---|
| lang | string | – | Optional BCP-47 language code, e.g. "en", "zh-CN", "es". Omit for the default track. |
| offset | integer | – | Optional. Character position to continue a long transcript from. Use the value given in the note at the end of the previous part. Omit to start from the beginning. |
| video | string | yes | YouTube video URL or 11-character video ID |
No output schema declared.
No examples provided.
list_channel_videos ~165
List the latest videos of a YouTube channel or playlist, with view count and duration. Use it to follow a creator who looks credible, or to cover a playlist. Returns at most 50 videos per call; to go further, call again with offset set to the number of videos already read (the result ends with the offset to use). Reaches up to the first 500 videos.
| Name | Type | Req | Description |
|---|---|---|---|
| channel | string | yes | A channel @handle (e.g. "@RachelsEnglish"), a channel or playlist URL. |
| limit | integer | – | How many videos. Default 20. |
| offset | integer | – | Optional. How many videos to skip, to read the next page. Use the value given at the end of the previous result. Default 0. |
No output schema declared.
No examples provided.
rank_channels_by_topic ~161
Find which channels talk about something the most, ranked by mentions, with how many of their videos mention it. Use it to find who covers a topic: creators to follow, experts, or partners. Same library, caption quirks and dates as search_spoken_words.
| Name | Type | Req | Description |
|---|---|---|---|
| also_match | array | – | Other spellings or mis-hearings to count as the same thing. Up to 5. |
| limit | integer | – | How many channels. Default 10. |
| query | string | yes | A word or short phrase (up to 8 words). |
| since | string | – | Only captions captured on or after this date, YYYY-MM-DD. |
| until | string | – | Only captions captured on or before this date, YYYY-MM-DD. |
No output schema declared.
No examples provided.
rank_videos_by_topic ~211
Find the videos that talk about something the most, ranked by how many sentences mention it. Better than searching titles when you want the videos that really go deep on a topic. Each result has the number of mentions, the first mention and a link. Read the best ones with get_youtube_transcript or find_in_transcript. Same library, caption quirks and dates as search_spoken_words.
| Name | Type | Req | Description |
|---|---|---|---|
| also_match | array | – | Other spellings or mis-hearings to count as the same thing. Up to 5. |
| channel | string | – | Only this channel: a channel ID (UC...) or part of the channel name. |
| limit | integer | – | How many videos. Default 10. |
| query | string | yes | A word or short phrase (up to 8 words). |
| since | string | – | Only captions captured on or after this date, YYYY-MM-DD. |
| until | string | – | Only captions captured on or before this date, YYYY-MM-DD. |
No output schema declared.
No examples provided.
search_spoken_words ~333
Search what people actually say inside YouTube videos. Full-text search over about 100 million spoken sentences from about 425,000 English-language videos (the ones users looked up on youtube-transcript.ai), with typically 1 to 8 million new sentences added every day. Returns matching sentences, each with the video, channel and a link that opens the video at that moment. Use it to find evidence and quotes, to see how people talk about a topic, product or phrase, or to find which videos mention something. Captions are auto-generated and often mis-hear names (for example "Claude Code" is often written "cloud code"), so pass likely mis-hearings in also_match. The library is a sample of YouTube, not all of it. Dates are the day we captured the captions, not the day the video was published.
| Name | Type | Req | Description |
|---|---|---|---|
| also_match | array | – | Other spellings or mis-hearings to count as the same thing, e.g. ["cloud code"]. Up to 5. |
| channel | string | – | Only this channel: a channel ID (UC...) or part of the channel name. |
| limit | integer | – | How many sentences to return. Default 10. |
| query | string | yes | A word or short phrase (up to 8 words), e.g. "claude code" or "break the ice". Plain words only, no search operators. |
| since | string | – | Only captions captured on or after this date, YYYY-MM-DD. |
| until | string | – | Only captions captured on or before this date, YYYY-MM-DD. |
No output schema declared.
No examples provided.
search_youtube_videos ~175
Search YouTube and return matching videos with channel, view count and duration. Use it first when researching a topic: run several differently-worded queries (and in more than one language), then read the best hits with get_youtube_transcript, find_in_transcript or get_transcripts_batch. Optional filters on views and length.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | How many videos to return. Default 15. |
| max_minutes | number | – | Drop videos longer than this many minutes. |
| min_minutes | number | – | Drop videos shorter than this many minutes. |
| min_views | integer | – | Drop videos with fewer views than this. |
| query | string | yes | Search words, e.g. "how I improved my English speaking" |
| sort | string | – | relevance (default) or date (newest first). |
No output schema declared.
No examples provided.
spoken_mentions_over_time ~221
Count how often something is mentioned over time, by day, week or month. Each period shows the mentions and the rate per million spoken sentences, so busy and quiet periods compare fairly. Use it to see whether a topic is rising or fading. The date is when we captured the captions, not when the video was published, and the first day (2026-09-13) holds a one-off backfill of earlier captions, so compare the rate, not the raw count, and be careful with that first period.
| Name | Type | Req | Description |
|---|---|---|---|
| also_match | array | – | Other spellings or mis-hearings to count as the same thing. Up to 5. |
| bucket | string | – | Period size. Default week. |
| channel | string | – | Only this channel: a channel ID (UC...) or part of the channel name. |
| query | string | yes | A word or short phrase (up to 8 words). |
| since | string | – | Start date, YYYY-MM-DD. |
| until | string | – | End date, YYYY-MM-DD. |
No output schema declared.
No examples provided.
How do I install the YouTube Transcript AI MCP server?
YouTube Transcript AI is a hosted endpoint at https://youtube-transcript.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · youtube-transcript.ai
claude mcp add --transport http ai-youtube-transcript-youtube-transcript 'https://youtube-transcript.ai/mcp'
What is the YouTube Transcript AI MCP server?
YouTube Transcript AI is an MCP server listed in the public MCP registry as ai.youtube-transcript/youtube-transcript. Read YouTube transcripts and search what people say across 425k videos. Free API key. This page covers its hosted endpoint (https://youtube-transcript.ai/mcp).
Is the YouTube Transcript AI MCP server safe to use?
YouTube Transcript AI scores 79 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the YouTube Transcript AI MCP server expose?
YouTube Transcript AI exposes 12 tools: get_youtube_transcript, search_youtube_videos, find_in_transcript, get_transcripts_batch, get_video_comments, and 7 more. Their descriptions and schemas cost roughly 2,098 tokens of context every time the server is loaded.
Does the YouTube Transcript AI MCP server require authentication?
No. We connected to YouTube Transcript AI without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the YouTube Transcript AI MCP server still maintained?
YouTube Transcript AI is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.