Transcriptapi MCP Server
io.transcriptapi/youtube-transcriptv0.1.1
YouTube transcripts, search, channels and playlists for AI agents, by transcriptapi.io.
context tax
~738 tok/turn5 tools
security
pending
cold start
pending
freshness
Active1d ago
Our reading of Transcriptapi, from the data
Transcriptapi is a images, video & audio MCP server, listed in the official MCP Registry.
Its 5 tools add about 738 tokens to every model turn, lighter than the images, video & audio median of 1,904 tokens across 298 measured servers (measured 2026-10-19).
Maintenance is active: the last public signal was in the last day (2026-10-17). For comparison, 73% of images, video & audio servers are active or maintained.
It runs either locally over stdio or as a hosted endpoint and needs one secret (TRANSCRIPTAPI_KEY); use a scoped, least-privilege key.
Install Transcriptapi MCP server
Install in Claude Code
claude mcp add transcriptapi -e TRANSCRIPTAPI_KEY='<transcriptapi-key>' -- npx -y transcriptapi-mcpInstall in Cursor
{
"mcpServers": {
"transcriptapi": {
"command": "npx",
"args": [
"-y",
"transcriptapi-mcp"
],
"env": {
"TRANSCRIPTAPI_KEY": "<transcriptapi-key>"
}
}
}
}Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).
Install in Claude Desktop
{
"mcpServers": {
"transcriptapi": {
"command": "npx",
"args": [
"-y",
"transcriptapi-mcp"
],
"env": {
"TRANSCRIPTAPI_KEY": "<transcriptapi-key>"
}
}
}
}Settings → Developer → Edit Config (claude_desktop_config.json), then restart.
Install in VS Code
{
"servers": {
"transcriptapi": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"transcriptapi-mcp"
],
"env": {
"TRANSCRIPTAPI_KEY": "<transcriptapi-key>"
}
}
}
}Add to .vscode/mcp.json in your workspace.
Install in Windsurf
{
"mcpServers": {
"transcriptapi": {
"command": "npx",
"args": [
"-y",
"transcriptapi-mcp"
],
"env": {
"TRANSCRIPTAPI_KEY": "<transcriptapi-key>"
}
}
}
}Add to ~/.codeium/windsurf/mcp_config.json.
Configuration
| Variable | Required | Secret | Description |
|---|---|---|---|
| TRANSCRIPTAPI_KEY | yes | yes | TranscriptAPI key (ta_...). Free at https://transcriptapi.io/login |
Remote endpoints
- streamable-http
https://api.transcriptapi.io/mcp
Context tax
Connecting this server adds ~738 tokens of tool definitions to every model turn (lean, 5 tools). Measured 2026-10-19 via its hosted endpoint; o200k tokenizer, worst case for clients that load all tools up front. How we measure
| Model | Per 1,000 turns | With prompt caching |
|---|---|---|
| Claude Opus 5.5 | $2.95 | $0.148 |
| Claude Sonnet 5.5 | $1.48 | $0.148 |
| Claude Haiku 5.5 | $0.074 | — |
Input prices as of 2026-10-06. Excludes your own prompt and output.
Tools (5)
get_youtube_transcript217 tokFetch 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.
search_channel_videos107 tokSearch for videos inside one YouTube channel by keyword — 'find the video where <channel> talks about <topic>'. Accepts a channel id, @handle or channel URL.
get_channel_videos103 tokList 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.
get_playlist_videos98 tokList 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.
search_youtube92 tokSearch 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.
Freshness
Active — last maintenance signal 1d ago. The newest of the signals below sets the band.
Last commit (default branch)
no data · GitHub
Latest release
no data · GitHub
Package published
no data · npm/PyPI
Registry entry updated
2026-10-17 · 1d ago · official registry · v0.1.1
How it compares in Images, Video & Audio
Against the most-starred images, video & audio servers we index. Token cost is per model turn, measured from each server's live tool list.
| Server | Stars | Tools | Tokens / turn | Freshness | Runs |
|---|---|---|---|---|---|
| Transcriptapi (this) | — | 5 | 738 | Active | local + hosted |
| Screenpipe | 21,982 | — | not measured | Active | — |
| screenpipe | 21,982 | — | not measured | Active | local |
| FunASR | 20,748 | — | not measured | Active | local |
| Agent-Native Analytics | 7,433 | — | not measured | Active | hosted |
| Remove AI Watermarks | 6,054 | — | not measured | Active | local |
FAQ
›How do I install the Transcriptapi MCP server in Claude Code?
Run: claude mcp add transcriptapi -e TRANSCRIPTAPI_KEY='<transcriptapi-key>' -- npx -y transcriptapi-mcp. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.
›Does Transcriptapi require an API key?
Yes. It expects TRANSCRIPTAPI_KEY, of which 1 is a secret.
›Can I use Transcriptapi as a remote (hosted) MCP server?
Yes — it offers both a hosted endpoint and a local stdio package.
›Is Transcriptapi in the official MCP registry?
Yes, as io.transcriptapi/youtube-transcript.
›How many tokens does Transcriptapi add to my context?
Its tool definitions total about 738 tokens, resent on every turn.
Sources and method
- Official MCP Registry entry
- updated 2026-10-17
- Package registry (npm / PyPI)
- listed
- Tool list (tools/list), measured by us
- 2026-10-19
- Last checked against all sources
- 2026-10-19
The description, packages and links come from the maintainer's own published metadata. Token cost, security signals, freshness and the reading above are MCPSkillHub's own measurements; see the methodology. Spot an error? Request a correction or claim the listing.
Alternatives to Transcriptapi
Other images, video & audio MCP servers.