TranscriptAPI — YouTube transcripts (transcriptapi.io) is an MCP server published by io.transcriptapi, hosted at api.transcriptapi.io. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 5 tools, including get_youtube_transcript, search_youtube, get_channel_videos, search_channel_videos, get_playlist_videos.
YouTube transcripts, search, channels and playlists for AI agents, by transcriptapi.io.
Nothing else in the archive shares these values.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Fetch the transcript (captions/subtitles) of a YouTube video as text. Accepts a watch URL, youtu.be link, Shorts link or bare 11-character video id. Returns the spoken text with timestamps grouped in ~30 s blocks by default; format 'text' is prose without timestamps, 'srt'/'vtt' are subtitle files, 'json' is raw segments with start/duration. Works with creator-uploaded and auto-generated captions. translate_to translates the transcript with AI (extra credits, scales with length) — omit unless asked.
| Parameter | Type | Description |
|---|---|---|
| video * | string | |
| format | string | |
| language | string | |
| translate_to |
None yet. Changes appear after a server's second daily check.
| any |
{
"name": "get_youtube_transcript",
"title": "Get YouTube transcript",
"description": "Fetch the transcript (captions/subtitles) of a YouTube video as text. Accepts a watch URL, youtu.be link, Shorts link or bare 11-character video id. Returns the spoken text with timestamps grouped in ~30 s blocks by default; format 'text' is prose without timestamps, 'srt'/'vtt' are subtitle files, 'json' is raw segments with start/duration. Works with creator-uploaded and auto-generated captions. translate_to translates the transcript with AI (extra credits, scales with length) — omit unless asked.",
"inputSchema": {
"type": "object",
"title": "get_youtube_transcriptArguments",
"required": [
"video"
],
"properties": {
"video": {
"type": "string",
"title": "Video"
},
"format": {
"type": "string",
"title": "Format",
"default": "timestamped"
},
"language": {
"type": "string",
"title": "Language",
"default": "en"
},
"translate_to": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Translate To",
"default": null
}
}
},
"outputSchema": {
"type": "object",
"title": "get_youtube_transcriptOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Search YouTube for videos by keyword. Returns video ids, titles, channel names, durations and view counts. Use a returned id with get_youtube_transcript to read it.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| query * | string |
{
"name": "search_youtube",
"title": "Search YouTube",
"description": "Search YouTube for videos by keyword. Returns video ids, titles, channel names, durations and view counts. Use a returned id with get_youtube_transcript to read it.",
"inputSchema": {
"type": "object",
"title": "search_youtubeArguments",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 10
},
"query": {
"type": "string",
"title": "Query"
}
}
},
"outputSchema": {
"type": "object",
"title": "search_youtubeOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}List the most recent uploads of a YouTube channel, newest first. Accepts a channel id (UC…), a handle (@name) or a channel URL. Returns ids, titles, durations, view counts and publish dates.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| channel * | string |
{
"name": "get_channel_videos",
"title": "List a channel's videos",
"description": "List the most recent uploads of a YouTube channel, newest first. Accepts a channel id (UC…), a handle (@name) or a channel URL. Returns ids, titles, durations, view counts and publish dates.",
"inputSchema": {
"type": "object",
"title": "get_channel_videosArguments",
"required": [
"channel"
],
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 20
},
"channel": {
"type": "string",
"title": "Channel"
}
}
},
"outputSchema": {
"type": "object",
"title": "get_channel_videosOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Search for videos inside one YouTube channel by keyword — 'find the video where <channel> talks about <topic>'. Accepts a channel id, @handle or channel URL.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| query * | string | |
| channel * | string |
{
"name": "search_channel_videos",
"title": "Search within a channel",
"description": "Search for videos inside one YouTube channel by keyword — 'find the video where <channel> talks about <topic>'. Accepts a channel id, @handle or channel URL.",
"inputSchema": {
"type": "object",
"title": "search_channel_videosArguments",
"required": [
"channel",
"query"
],
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 10
},
"query": {
"type": "string",
"title": "Query"
},
"channel": {
"type": "string",
"title": "Channel"
}
}
},
"outputSchema": {
"type": "object",
"title": "search_channel_videosOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}List the videos in a YouTube playlist, in playlist order. Accepts a playlist URL (anything with list=…) or the playlist id. Returns ids and titles for get_youtube_transcript.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| playlist * | string |
{
"name": "get_playlist_videos",
"title": "List a playlist's videos",
"description": "List the videos in a YouTube playlist, in playlist order. Accepts a playlist URL (anything with list=…) or the playlist id. Returns ids and titles for get_youtube_transcript.",
"inputSchema": {
"type": "object",
"title": "get_playlist_videosArguments",
"required": [
"playlist"
],
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 50
},
"playlist": {
"type": "string",
"title": "Playlist"
}
}
},
"outputSchema": {
"type": "object",
"title": "get_playlist_videosOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Tools for reading YouTube through TranscriptAPI. Use get_youtube_transcript to read what is said in a video (pass the URL the user gave you — ids are extracted automatically). Use search_youtube to find videos, get_channel_videos / search_channel_videos to list or search a channel's uploads, and get_playlist_videos for playlists. Each successful call costs the user one API credit; transcripts are cached, so repeating the same video is free. Videos without captions (disabled, private, age-restricted, deleted) cannot be read — tell the user rather than retrying.
Names, descriptions and schemas were written by the server and are shown as data.