Minuta
Discovers uploads from YouTube channels via the Data API and extracts timestamped transcripts through a resilient provider chain (transcriptapi, apify, supadata, ytdlp, yta), turning channel content into a searchable, citable knowledge base with video IDs, exact [HH:MM:SS] timestamps, and ?t= links.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
TURN YOUTUBE INTO YOUR KNOWLEDGE BASE
Point Minuta at the channels you learn from. It keeps every word, timestamped — so you or any AI agent can answer from them, write like them, think with them.
Quickstart · Docs · Keys · Operations · llms.txt · AGENTS.md
Minuta (n.) — the written minutes of a proceeding. The raw material is the record; the product is what you make with it.
● What you make with it
Answers from voices you trust — ask across 200 videos at once; every claim comes back cited with video, timestamp, and link. No generic AI slop.
Drafts in their voice — scripts, posts, newsletters, ghostwriting, grounded in what was actually said, phrased the way it was said.
A thinking partner — refer back for ideas, check what was argued where, build on lines of thought instead of rewatching.
A library that compounds — new uploads sync automatically; the base only gets more useful.
Point Minuta at a channel. It discovers every upload, extracts timestamped transcripts through a resilient provider chain, stores canonical JSON + Markdown privately, embeds every chunk, and serves it all over REST and remote MCP — so you, or any AI agent, can search 200 videos as easily as one.
flowchart LR
YT[YouTube] -->|Data API: discovery only| D[discover]
D --> P{provider chain}
P -->|transcriptapi · supadata · apify · ytdlp · yta| C[canonical doc]
C --> R2[(R2 private bucket)]
C --> PG[(Supabase + pgvector)]
PG --> API[REST + MCP]Related MCP server: tubescout
● Why it holds up
Problem | What Minuta does |
YouTube transcripts are scattered, rate-limited, IP-blocked | Ordered provider chain with honest error taxonomy — definitive answers stick, transient ones back off with cooldowns, never mislabeled |
Timestamps get destroyed by exporters | Canonical format preserves millisecond timing end-to-end; untimed sources stay honestly untimed |
Agents hallucinate video claims | Every passage carries video ID + |
Re-fetching duplicates everything | Content-hash identity: identical text always resolves to one version, one chunk set |
● Quickstart
You bring: Supabase Postgres, Cloudflare R2 bucket, YouTube Data API key, one transcript route (Apify token or nothing for the free paths). Full key guide: docs/KEYS.md.
git clone https://github.com/AdarshJ173/minuta && cd minuta
bash scripts/setup.sh # venv + deps, never overwrites .env
# fill .env (DATABASE_URL, R2_*, YOUTUBE_API_KEY, ADMIN_BOOTSTRAP_TOKEN, + provider)
PYTHONPATH=src python -m minuta.migrate
PYTHONPATH=src pytest -q # offline suite, no network, no keys
# add a channel, backfill it, search it
TOKEN=<bootstrap>
curl -X POST $PUBLIC_BASE_URL/admin/channels -H "Authorization: Bearer $TOKEN" \
-d '{"input":"@somehandle"}'
PYTHONPATH=src python scripts/backfill.py --max 200 --sleep 15
curl "$PUBLIC_BASE_URL/v1/search?q=your+question" -H "Authorization: Bearer $READER_KEY"Deploy — Modal (API + 5-min worker + one-shot backfill) or any Docker host. See docs/OPERATIONS.md. Typical full-channel cost: ~$0.11. Paying for speed? docs/TURBO.md is the paid fastest path: realtime transcript API, hosted embeddings, parallel fan-out — under $1 per 200-video channel after base plans.
● Transcript providers
First configured success wins (TRANSCRIPT_PROVIDER_ORDER).
Provider | Key needed | Notes |
|
| Realtime REST, fastest (~49ms median). The turbo pick. |
|
| Store actor, timestamped JSON, ~$0.70/1k. Reliable but slow (one Actor run/video). |
| none | Subtitle-only VTT, manual-first. Often HTTP 429 from cloud IPs. |
| none |
|
|
| Paid API fallback, ~$0.99/1k at volume. |
Paid fastest order: transcriptapi,supadata,apify. Full guide: docs/TURBO.md.
Only definitive per-video outcomes are permanent (TranscriptNotFound,
removed, age-restricted). Inconclusive results retry; a blocked fallback
never triggers a global cooldown when the primary already answered.
Rules: AGENTS.md · logic: src/minuta/transcripts/pipeline.py.
● For agents
Point any MCP-capable agent at $PUBLIC_BASE_URL/mcp (Streamable HTTP,
Bearer token) or hand it this paragraph with your question appended —
template in docs/AGENTS_PROMPT.md. Machine-readable
surface: llms.txt. Repo rules agents must obey: AGENTS.md.
● Layout
minuta/
├── src/minuta/ # all code
│ ├── transcripts/ # providers (transcriptapi, apify, ytdlp, remote) + pipeline chain
│ ├── api.py mcp.py worker.py ingest.py search.py index.py
│ └── settings.py db.py store.py auth.py jobs.py provider_state.py
├── migrations/ # Postgres + pgvector + FTS schema
├── scripts/ # setup.sh backfill.py make_secret.sh
├── tests/ # offline only — MockTransport, no network
├── docs/ # ARCHITECTURE KEYS OPERATIONS AGENTS_PROMPT
├── llms.txt AGENTS.md modal_app.py Dockerfile● Contributing & security
PRs welcome: keep commits small, ruff + pytest green, tests stay offline.
See CONTRIBUTING.md. To report a vulnerability, see
SECURITY.md — please don't open public issues for secrets or
auth bypasses.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
YouTube transcripts, search, channel/playlist listings and upload tracking for AI agents.
Transcripts, summaries, chapters and timestamped search for video links, for AI agents.
Search and cite timestamped YouTube and podcast transcripts; transcribe any video or episode.
YouTube transcripts for AI agents: 150+ languages, AI transcription fallback, search, summaries.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceBuilds a searchable knowledge base from YouTube video transcripts with hybrid semantic and keyword search. Allows LLM assistants to search, organize, and retrieve timestamped information from videos you've watched.3-
- AlicenseAqualityCmaintenanceEnables AI agents to search YouTube like a database, retrieve transcripts and channel data, and mine videos for claims, numbers, and demand signals — without needing an API key.6146 npmMIT
- AlicenseAqualityBmaintenanceEnables AI agents to search videos, retrieve metadata and transcripts, pinpoint exact moments via hybrid semantic search, and conduct multi-video research with timestamp deep links—all without YouTube API keys.51MIT
- AlicenseAqualityCmaintenanceEnables AI assistants to fetch YouTube transcripts with timestamps, search within a video, and keep a local searchable memory of every transcript fetched.4MIT