# Stand up a research library your whole team queries

> Curate once, query forever: shared imports become a common brain with citations instead of link-dump Slack threads.

- For: Chief of Staff
- Category: Team Knowledge & Library Ops
- MCP tools: library_import_youtube_channel, library_search, deep_context
- HTML version: https://veridive.com/mcp/use-cases/company-research-library

## The problem

Every team has the person who "knows where that talk is". Maybe it's you. The research your company runs on — conference talks, competitor launches, expert interviews, your own webinars — lives in watch-later lists, dead Slack links and someone's memory. When a decision needs the source, the ritual begins: who watched it, which video was it, twenty minutes of scrubbing for one quote.

A link dump is write-only memory. What you actually want is a **curated library that answers questions**: one place where the channels that matter are imported, transcripts and all, and where "didn't their CTO explain exactly this on stage?" takes seconds to answer — with a citation to the moment, not a vibe.

## How veridive MCP helps

**library_import_youtube_channel** does the curating: point it at a channel or playlist — a conference archive, a competitor's channel, your own webinar backlog — and it imports every video into your veridive library, transcripts included. **library_search** and its sibling library_list are your card catalog: find items by title, tag or type in an instant, free.

**deep_context** is where the library earns its keep. Pick the imported talks that matter — your assistant scopes a selection by their library IDs — and ask your real question across them. It runs the full research pipeline over those transcripts and returns a grounded answer where **every claim cites the exact chunk of the exact talk**, so nobody has to rewatch anything to trust it.

And because the connection is just an MCP config, the library isn't locked to your machine: share the connector setup the way your team already shares tool configs — a project-level mcp.json in the repo, a shared Claude connector — and the same curated brain answers inside everyone's assistant.

## How to run it

1. **Connect veridive MCP** — One-time setup: add the veridive MCP server to Claude, ChatGPT, Cursor or any MCP client and generate your API key. Takes about two minutes.
2. **Curate the shelves** — Import the channels and playlists your team keeps coming back to. Imports are charged per video, so start with the archives that answer real questions — you can always add more.

   ```
   Import this conference's YouTube channel into my veridive library: <channel URL>. Skip Shorts. Use veridive's library_import_youtube_channel.
   ```
3. **Find the right items fast** — The library tools are your catalog: search titles, filter by tag or type, list what's on the shelf. This is how you (or your assistant) pick the talks a question should be scoped to.

   ```
   List what's in my library from that conference import — I want the talks about pricing and packaging.
   ```
4. **Ask the library, get citations back** — Your assistant scopes deep_context to the selected talks and asks your question. The answer comes back grounded, citing the exact transcript chunks — ready to paste into the doc or the deck.

   ```
   Across those talks: where did speakers disagree about usage-based pricing, and what were the strongest arguments on each side? Cite the talks and the moments.
   ```

## Problems it solves

- Institutional knowledge trapped in one person's memory and a hundred watch-later links nobody revisits.
- "Can you send me that talk?" threads that end with twenty minutes of scrubbing video for a single quote.
- Research gets repeated because nobody can check what was already watched, imported or concluded.
- Slack link dumps are write-only: the knowledge goes in, nothing ever comes back out.

## Why it's valuable

- Curate once, answer forever — a cited answer in seconds instead of "let me find that video for you".
- Answers cite the exact moment in the exact talk, so people can verify without rewatching an hour of video.
- The library compounds: every imported channel makes every future question better answered.
- It plugs into the assistants your team already uses via a shareable MCP config — rolling it out is sharing a file, not adopting a platform.

## Example prompts

```
Import this channel into my veridive library, skip Shorts: <channel URL> — use veridive's library_import_youtube_channel.
```

```
List the talks in my library about pricing, then ask across them: where do the speakers disagree? Cite the moments.
```

```
From the imported competitor launch videos: what did they promise about their roadmap, word for word, and in which video?
```

## FAQ

**What can I import?**

Single videos, whole channels, or playlists — library_import_youtube_video and library_import_youtube_channel cover all three, transcripts included. Channel imports can optionally include Shorts and live streams. Imports are charged per video; searching and listing your library is free.

**How does the whole team get access?**

An MCP connection is just configuration. Share the connector setup the way you already share tool configs — a project-level mcp.json in a repo, or a shared connector in your team's assistant — and everyone's AI queries the same curated library.

**What's the difference between searching and asking?**

library_search and library_list are the catalog: instant, free lookups over titles, tags and types — they find the right items. deep_context is the reading room: it takes a selection of items and answers questions across their transcripts with citations. Locate with search, understand with context.

**Do I have to name the tools in my prompts?**

No. Your assistant picks the right veridive tool from a plain-language request — "import this channel" or "what does my library say about X" route themselves. Naming helps only when several servers could plausibly handle the request.

## Related use cases

- [Build a living competitor dossier your team can query](https://veridive.com/mcp/use-cases/living-competitor-dossier.md) — One shared library of rival content, searchable and chat-able — new teammates stop asking "where's the competitor doc?"
- [Assemble a new-hire ramp kit from curated videos](https://veridive.com/mcp/use-cases/new-hire-ramp-kit.md) — Point new hires at the library, generate study notes per module, and let them ask the library questions instead of you.
- [Make your own webinars institutional memory](https://veridive.com/mcp/use-cases/own-webinar-institutional-memory.md) — Import your company's channel; three years of webinars stop being dead links and start answering questions.

---

Part of the veridive MCP use-case library: https://veridive.com/mcp/use-cases.md
Server docs for agents: https://veridive.com/mcp.md