# Spring-clean a messy shared library

> List, filter and search what's actually in there — find the duplicates and the gaps before adding more.

- For: Ops
- Category: Team Knowledge & Library Ops
- MCP tools: library_list, library_search
- HTML version: https://veridive.com/mcp/use-cases/library-spring-cleaning

## The problem

Shared libraries follow the same entropy curve as shared drives: enthusiastic curation, then accumulation, then a state where nobody's sure what's in there, three tags mean the same thing, and the safest move is importing the video again just in case — which is how the mess funds its own growth.

The fix isn't discipline; it's visibility. A library you can actually see — what's in it, how it's tagged, where the duplicates cluster, which topics are over-collected and which are gaps — is a library the team keeps using instead of abandoning for a fresh start that will entropy identically.

## How veridive MCP helps

**library_list** and **library_search** are the audit tools, and they're free — browsing costs nothing. List by tag and type to see the actual shape of the collection; search titles to find the duplicate imports and the near-duplicates; walk the tag landscape to find the three tags doing one tag's job.

The audit output drives the cleanup: a duplicate list, a tag-consolidation map, and — the valuable surprise — the gap list: topics the team assumes are covered and aren't. Twenty minutes quarterly keeps the library an asset; the alternative is the shared-drive death spiral, with import credits attached.

## 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. **Map what's actually there** — The full inventory by tag and type — the library's real shape, often surprising.

   ```
   List my library's contents grouped by tag — how many items per tag, and which items carry no tags at all?
   ```
3. **Hunt the duplicates and tag-sprawl** — Title search finds the double imports; the tag map shows the synonyms.

   ```
   Search my library for likely duplicates — same or near-same titles — and list tags that look like synonyms of each other.
   ```
4. **Write the cleanup plan** — Consolidations, removals and the gap list — the part worth showing the team.

   ```
   From this audit: which tags should merge, what's duplicated, and which topics we reference often are actually missing from the library?
   ```

## Problems it solves

- Nobody knows what's in the shared library, so re-importing 'just in case' funds the mess.
- Tag sprawl — three names for one concept — quietly breaks every scoped query.
- Duplicates waste import credits and split any question's context across copies.
- Assumed coverage: the topics everyone thinks are in there and aren't.

## Why it's valuable

- The audit runs on free calls — visibility costs nothing.
- Scoped queries (deep_context) get sharper the moment tags consolidate.
- The gap list turns the next import budget into deliberate curation.
- Quarterly twenty minutes beats the fresh-start-and-re-entropy cycle every team knows.

## Example prompts

```
List library contents by tag — counts per tag, untagged items flagged.
```

```
Find likely duplicate imports and synonym tags.
```

```
Cleanup plan: merges, removals, and the missing-topics list.
```

## FAQ

**Does the audit cost credits?**

No — library_list and library_search are free calls. The whole audit is browsing; credits only enter if you decide to import the gap list.

**Can tags be renamed in bulk from here?**

The audit produces the consolidation map; applying tag changes happens in veridive's library UI. The MCP layer is the visibility half — which was the missing half.

**How does the search work for finding duplicates?**

library_search matches against item titles — same-title and near-title imports surface immediately. For content-level near-duplicates (same talk uploaded by two channels), the title patterns usually give them away too.

## Related use cases

- [Stand up a research library your whole team queries](https://veridive.com/mcp/use-cases/company-research-library.md) — Curate once, query forever: shared imports become a common brain with citations instead of link-dump Slack threads.
- [Send a weekly digest of new library imports](https://veridive.com/mcp/use-cases/weekly-import-digest.md) — List the week's additions and draft a newsletter-style digest — the team reads one email instead of watching six hours.
- [Know your burn across research sprints](https://veridive.com/mcp/use-cases/know-your-burn.md) — Query balance and daily quota mid-sprint — plan heavy research days around what's actually left.

---

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