_ registry / mcp streamable-http · checked 1h ago

YouTube Transcript AI

listed under this name in a public catalogue; the server gives only its address, youtube-transcript.ai

https://youtube-transcript.ai

Registry code: f2637314c1285070

api record

Call these tools one at a time, not in parallel: the server allows about 10 requests per 10 seconds per client, and a burst gets an HTTP 429 with Retry-After: 10. If you get a 429, wait 10 seconds and retry. To cover several videos, prefer get_transcripts_batch (up to 5 per call) over many separate calls, and use find_in_transcript instead of reading whole transcripts. To find what people say about a topic across many videos, start with search_spoken_words; captions often mis-hear names, so pass likely mis-hearings in also_match.

endpoint
https://youtube-transcript.ai/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is YouTube Transcript AI live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is YouTube Transcript AI free to use?
Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.
What tools does YouTube Transcript AI have?
12 tools: find_in_transcript, get_spoken_context, rank_channels_by_topic, rank_videos_by_topic, spoken_mentions_over_time, get_video_comments, get_account_status, search_youtube_videos, ….
Is YouTube Transcript AI safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 99.7%· all time 99.7%

latency
322ms

last good check

priced tools
0

of 12 tools

_ answered our checks, 90 days 719 checks · signed record
  • down → live
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· timeout after 20000ms
_ what it is for
topic
media understanding speech to text
used for
  • get the transcript of a youtube video
takes → gives
video → text
tools
1 reads
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 12 tools
12 auth-required 12 of 12 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • find_in_transcript auth-required 14h ago

    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).

    mcp-tool

    {
  "type": "object",
  "required": [
    "video",
    "keywords"
  ],
  "properties": {
    "lang": {
      "type": "string",
      "description": "Optional BCP-47 caption language code. Omit for the default track."
    },
    "video": {
      "type": "string",
      "description": "YouTube video URL or 11-character video ID"
    },
    "context": {
      "type": "integer",
      "maximum": 3,
      "minimum": 0,
      "description": "Paragraphs (about 30 seconds each) to include before and after each match. Default 1."
    },
    "keywords": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Words or short phrases to look for (up to 8). A passage matches if it contains any of them."
    },
    "max_hits": {
      "type": "integer",
      "maximum": 20,
      "minimum": 1,
      "description": "Maximum passages to return. Default 8."
    }
  }
}
    arguments 36 lines
  • get_spoken_context auth-required 14h ago

    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.

    mcp-tool

    {
  "type": "object",
  "required": [
    "video",
    "seconds"
  ],
  "properties": {
    "video": {
      "type": "string",
      "description": "YouTube video ID or URL, as returned by search_spoken_words."
    },
    "window": {
      "type": "integer",
      "maximum": 120,
      "minimum": 5,
      "description": "Seconds to include before and after. Default 20."
    },
    "seconds": {
      "type": "number",
      "minimum": 0,
      "description": "The moment to read around, in seconds from the start of the video."
    }
  }
}
    arguments 24 lines
  • rank_channels_by_topic auth-required 1h ago

    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.

    mcp-tool

    {
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 30,
      "minimum": 1,
      "description": "How many channels. Default 10."
    },
    "query": {
      "type": "string",
      "description": "A word or short phrase (up to 8 words)."
    },
    "since": {
      "type": "string",
      "description": "Only captions captured on or after this date, YYYY-MM-DD."
    },
    "until": {
      "type": "string",
      "description": "Only captions captured on or before this date, YYYY-MM-DD."
    },
    "also_match": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Other spellings or mis-hearings to count as the same thing. Up to 5."
    }
  }
}
    arguments 33 lines
  • rank_videos_by_topic auth-required 1h ago

    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.

    mcp-tool

    {
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 30,
      "minimum": 1,
      "description": "How many videos. Default 10."
    },
    "query": {
      "type": "string",
      "description": "A word or short phrase (up to 8 words)."
    },
    "since": {
      "type": "string",
      "description": "Only captions captured on or after this date, YYYY-MM-DD."
    },
    "until": {
      "type": "string",
      "description": "Only captions captured on or before this date, YYYY-MM-DD."
    },
    "channel": {
      "type": "string",
      "description": "Only this channel: a channel ID (UC...) or part of the channel name."
    },
    "also_match": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Other spellings or mis-hearings to count as the same thing. Up to 5."
    }
  }
}
    arguments 37 lines
  • spoken_mentions_over_time auth-required 1h ago

    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.

    mcp-tool

    {
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "description": "A word or short phrase (up to 8 words)."
    },
    "since": {
      "type": "string",
      "description": "Start date, YYYY-MM-DD."
    },
    "until": {
      "type": "string",
      "description": "End date, YYYY-MM-DD."
    },
    "bucket": {
      "enum": [
        "day",
        "week",
        "month"
      ],
      "type": "string",
      "description": "Period size. Default week."
    },
    "channel": {
      "type": "string",
      "description": "Only this channel: a channel ID (UC...) or part of the channel name."
    },
    "also_match": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Other spellings or mis-hearings to count as the same thing. Up to 5."
    }
  }
}
    arguments 40 lines
  • get_video_comments auth-required 6h ago

    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.

    mcp-tool

    {
  "type": "object",
  "required": [
    "video"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1,
      "description": "How many comments. Default 30."
    },
    "video": {
      "type": "string",
      "description": "YouTube video URL or 11-character video ID"
    }
  }
}
    arguments 18 lines
  • get_account_status auth-required 14h ago

    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.

    mcp-tool

    {
  "type": "object",
  "properties": {}
}
    arguments 4 lines
  • search_youtube_videos auth-required 21h ago

    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.

    mcp-tool

    {
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "sort": {
      "enum": [
        "relevance",
        "date"
      ],
      "type": "string",
      "description": "relevance (default) or date (newest first)."
    },
    "limit": {
      "type": "integer",
      "maximum": 30,
      "minimum": 1,
      "description": "How many videos to return. Default 15."
    },
    "query": {
      "type": "string",
      "description": "Search words, e.g. \"how I improved my English speaking\""
    },
    "min_views": {
      "type": "integer",
      "minimum": 0,
      "description": "Drop videos with fewer views than this."
    },
    "max_minutes": {
      "type": "number",
      "minimum": 0,
      "description": "Drop videos longer than this many minutes."
    },
    "min_minutes": {
      "type": "number",
      "minimum": 0,
      "description": "Drop videos shorter than this many minutes."
    }
  }
}
    arguments 41 lines
  • get_youtube_transcript reads auth-required 21h ago

    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.

    mcp-tool

    {
  "type": "object",
  "required": [
    "video"
  ],
  "properties": {
    "lang": {
      "type": "string",
      "description": "Optional BCP-47 language code, e.g. \"en\", \"zh-CN\", \"es\". Omit for the default track."
    },
    "video": {
      "type": "string",
      "description": "YouTube video URL or 11-character video ID"
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "description": "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."
    }
  }
}
    arguments 21 lines
  • search_spoken_words auth-required 21h ago

    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.

    mcp-tool

    {
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 30,
      "minimum": 1,
      "description": "How many sentences to return. Default 10."
    },
    "query": {
      "type": "string",
      "description": "A word or short phrase (up to 8 words), e.g. \"claude code\" or \"break the ice\". Plain words only, no search operators."
    },
    "since": {
      "type": "string",
      "description": "Only captions captured on or after this date, YYYY-MM-DD."
    },
    "until": {
      "type": "string",
      "description": "Only captions captured on or before this date, YYYY-MM-DD."
    },
    "channel": {
      "type": "string",
      "description": "Only this channel: a channel ID (UC...) or part of the channel name."
    },
    "also_match": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Other spellings or mis-hearings to count as the same thing, e.g. [\"cloud code\"]. Up to 5."
    }
  }
}
    arguments 37 lines
  • get_transcripts_batch auth-required 6h ago

    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.

    mcp-tool

    {
  "type": "object",
  "required": [
    "videos"
  ],
  "properties": {
    "lang": {
      "type": "string",
      "description": "Optional BCP-47 caption language code applied to every video."
    },
    "videos": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 5,
      "description": "YouTube URLs or 11-character video IDs (up to 5)."
    },
    "max_chars_each": {
      "type": "integer",
      "maximum": 30000,
      "minimum": 1000,
      "description": "Characters of transcript to keep per video. Default 6000."
    }
  }
}
    arguments 26 lines
  • list_channel_videos auth-required 6h ago

    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.

    mcp-tool

    {
  "type": "object",
  "required": [
    "channel"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1,
      "description": "How many videos. Default 20."
    },
    "offset": {
      "type": "integer",
      "maximum": 499,
      "minimum": 0,
      "description": "Optional. How many videos to skip, to read the next page. Use the value given at the end of the previous result. Default 0."
    },
    "channel": {
      "type": "string",
      "description": "A channel @handle (e.g. \"@RachelsEnglish\"), a channel or playlist URL."
    }
  }
}
    arguments 24 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id f2637314c1285070.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/f2637314c1285070/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/f2637314c1285070/badge.svg)](https://brick.blue/agent/f2637314c1285070?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.