# Trace a viral claim to its primary source

> Follow the citation chain to the original spoken statement — publish the correction with the receipt.

- For: Editor
- Category: Media, PR & Comms
- MCP tools: deep_query, library_import_youtube_video, get_youtube_transcript
- HTML version: https://veridive.com/mcp/use-cases/viral-claim-fact-check

## The problem

Every viral claim has a genealogy: someone said something, on camera, in context — then a clip cropped it, a caption sharpened it, an aggregator restated it, and by the fifth generation the claim circulating bears a family resemblance to the original at best. Your newsroom now has to decide: report the circulating version, debunk it, or ignore it. All three decisions require the one thing nobody in the chain has: the original.

Tracing genealogy manually means archaeology across reposts and reaction videos, each pointing vaguely at the last. But the original is almost always a public video — a full interview, a hearing, a keynote — and the distortion is almost always measurable: what was actually said, minus what's being shared.

## How veridive MCP helps

**deep_query** runs the genealogy hunt: give it the circulating claim and ask for the original source and full context. It researches across the spoken record — including the long-form originals that reaction clips crop from — and reports back **with citations**: who appears to have said it first, where, and what the surrounding conversation actually was.

**get_youtube_transcript** (after a quick import) delivers the forensic layer: the verbatim passage, the sentence before, the qualifier after, the question that prompted it. Now the story writes itself with receipts — "the viral clip omits the first half of the sentence, which reads..." — and the correction carries a timestamp instead of a counter-assertion. In the credibility economy, being the desk whose checks land this way compounds.

## 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. **Hunt the original** — Give the circulating claim and ask for its source — the research pipeline digs past the reposts to the long-form original.

   ```
   This claim is circulating: '<viral claim>'. Find the original spoken source — who said it, where, and in what context? Citations — use veridive's deep_query.
   ```
3. **Pull the forensic passage** — Import the original and get the verbatim transcript around the moment — the crop is usually visible immediately.

   ```
   Import this video and pull the transcript passage around the statement, with the question that prompted it and the sentences on both sides: <video link>
   ```
4. **Publish with the receipt** — Original vs circulating version, side by side, timestamped. The correction that ends arguments instead of starting them.

   ```
   Draft the fact-check: the circulating claim, the verbatim original with timestamp, and exactly what the viral version changed or omitted.
   ```

## Problems it solves

- Viral claims arrive fifth-generation; the original is buried under reposts pointing at each other.
- Manual genealogy across clips and reactions takes longer than the news cycle allows.
- Corrections without receipts read as opinion — assertion versus assertion, and virality wins.
- Cropped context is the dominant distortion mode, and only the full transcript exposes it.

## Why it's valuable

- The genealogy hunt runs in minutes, inside the news cycle instead of behind it.
- Corrections ship with the verbatim passage and timestamp — receipts, not rebuttals.
- The crop becomes demonstrable: here's the sentence, here's what the clip kept.
- Desk credibility compounds: your checks are the ones that end the argument.

## Example prompts

```
Circulating claim: '<claim>'. Find the original spoken source and context, cited — use veridive's deep_query.
```

```
Import <video link>, pull the verbatim passage around the statement with surrounding context.
```

```
Draft the fact-check: circulating vs original, timestamped, what changed.
```

## FAQ

**What if the claim never had a real source?**

Then the hunt documents that: no credible primary utterance found, only circular reposts. 'This claim has no traceable original' is itself a publishable, defensible finding.

**How does this differ from the extraordinary-claims check?**

That one audits whether evidence exists for a claim's substance (is the 40% yield real?); this one traces a quote's genealogy (did they actually say it, and in what context?). Newsrooms often need both on the same story.

**Which tools does this chain?**

deep_query for the genealogy hunt (it searches the long-form originals, not just the clips), then library_import_youtube_video + get_youtube_transcript for the verbatim forensic passage — free to pull once imported.

## Related use cases

- [Fact-check extraordinary claims in emerging assets](https://veridive.com/mcp/use-cases/extraordinary-claims-check.md) — "Guaranteed 40% yield" — ask for the primary sources behind a claim and get either citations or silence; both are answers.
- [Hunt sources with timestamped quotes](https://veridive.com/mcp/use-cases/timestamped-source-hunting.md) — Find who said it, pull the transcript, quote to the second — attribution your editor can verify in one click.
- [Vet a market claim before repeating it to your board](https://veridive.com/mcp/use-cases/vet-claims-before-the-board.md) — That stat in your deck — trace it to a primary spoken source with evidence filters, or find out it dissolves under scrutiny.

---

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