YouTube Live Stream & Replay Chat Extractor: MCP config, n8n workflow and API

{
  "videoRefs": [
    "https://www.youtube.com/watch?v=FQbNtLOVlwU"
  ],
  "mode": "auto",
  "channelDiscoveryMode": "current_live",
  "maxVideosPerChannel": 1,
  "lookbackDays": 30,
  "includeUpcomingLives": false,
  "maxMessagesPerVideo": 3,
  "maxTotalItems": 3,
  "maxTimePerVideoSecs": 120,
  "includeNormalMessages": true,
  "includeSuperChats": true,
  "includeMembershipEvents": true,
  "includeGiftEvents": true,
  "includeSystemEvents": true,
  "includePlaceholders": false,
  "includeSummary": false,
  "startOffsetSecs": 0,
  "endOffsetSecs": 0,
  "liveCollectSecs": 10,
  "pollIntervalMs": 2000,
  "language": "en",
  "regionCode": "US",
  "includeMetadata": true
}

---
name: youtube-live-stream-and-replay-chat-extractor
description: "Chat events with authors, replay offsets, Super Chat and gift amounts, membership detail, badges, stream metadata and optional summaries. Runs the Apify Actor dataspryva/youtube-live-stream-and-replay-chat-extractor. Use when the user needs YouTube data with fields such as videoId, eventType, authorName, messageText, videoOffsetText, amountText and an Apify token is available."
compatibility: "Needs network access, curl, and an APIFY_TOKEN environment variable. Runs are billed to the token owner's Apify account."
metadata:
  actor: "dataspryva/youtube-live-stream-and-replay-chat-extractor"
  store-url: "https://apify.com/dataspryva/youtube-live-stream-and-replay-chat-extractor"
---

# YouTube Live Stream & Replay Chat Extractor

Use this skill to fetch YouTube data with the Apify Actor `dataspryva/youtube-live-stream-and-replay-chat-extractor` and work with the returned rows.

## Before running

1. Check that `APIFY_TOKEN` is set in the environment. Never print it or write it to a file.
2. Build `input.json` from the user's request using the fields below. Keep limits small for a first run.
3. Confirm the search terms or URLs with the user if the request is ambiguous.

## Input fields

| Field | Type | Meaning |
| --- | --- | --- |
| `videoRefs` | array | YouTube watch, live, shorts or youtu.be links, 11-character video IDs, or a channel live link such as @handle/live. |
| `mode` | one of `auto`, `active`, `replay` | Auto detects live versus replay. Active captures an ongoing live chat. Replay reads the saved chat of an ended stream. |
| `channelDiscoveryMode` | one of `current_live`, `current_live_then_replays`, `latest_replays` | Which streams to pick from each channel. Used with channel references. |
| `maxVideosPerChannel` | integer | Maximum streams to process from each channel. |
| `lookbackDays` | integer | How far back to include ended streams from a channel. Use 0 for no limit. |
| `includeUpcomingLives` | boolean | Emit an upcoming status row for scheduled channel streams instead of skipping them. |
| `maxMessagesPerVideo` | integer | Maximum unique chat events collected from each video. Use 0 to collect every available event. |
| `maxTotalItems` | integer | Whole-run cap across all videos and summary rows. Use 0 for no limit. |
| `maxTimePerVideoSecs` | integer | Safety limit for replay pagination on one video, in seconds. A run that reaches it reports partial_capture. |
| `includeNormalMessages` | boolean | Include standard text chat messages. |
| `includeSuperChats` | boolean | Include paid Super Chat messages and paid Super Stickers. |
| `includeMembershipEvents` | boolean | Include new and renewed channel membership events. |
| `includeGiftEvents` | boolean | Include gift membership purchases, gift membership redemptions and paid gift messages. |
| `includeSystemEvents` | boolean | Include engagement notices, slow-mode changes, restricted participation and other system rows. |

Example `input.json` (the Actor's published prefill):

```json
{
  "videoRefs": [
    "https://www.youtube.com/watch?v=FQbNtLOVlwU"
  ],
  "mode": "auto",
  "channelDiscoveryMode": "current_live",
  "maxVideosPerChannel": 1,
  "lookbackDays": 30,
  "includeUpcomingLives": false,
  "maxMessagesPerVideo": 3,
  "maxTotalItems": 3,
  "maxTimePerVideoSecs": 120,
  "includeNormalMessages": true,
  "includeSuperChats": true,
  "includeMembershipEvents": true,
  "includeGiftEvents": true,
  "includeSystemEvents": true,
  "includePlaceholders": false,
  "includeSummary": false,
  "startOffsetSecs": 0,
  "endOffsetSecs": 0,
  "liveCollectSecs": 10,
  "pollIntervalMs": 2000,
  "language": "en",
  "regionCode": "US",
  "includeMetadata": true
}
```

## Run

```bash
curl -sS -X POST "https://api.apify.com/v2/acts/dataspryva~youtube-live-stream-and-replay-chat-extractor/run-sync-get-dataset-items" \
  -H "Authorization: Bearer $APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d @input.json > results.json
```

The call waits for the run to finish and returns the dataset items as a JSON array. If the run needs more than 300 seconds the API answers with HTTP 408; then start the run with `POST /v2/acts/dataspryva~youtube-live-stream-and-replay-chat-extractor/runs`, poll `GET /v2/actor-runs/{runId}` until `SUCCEEDED`, and read `GET /v2/datasets/{defaultDatasetId}/items`.

## Output

Each item is one record. Published fields include: `videoId`, `eventType`, `authorName`, `messageText`, `videoOffsetText`, `amountText`, `currency`, `amountValue`, `giftCount`, `videoTitle`, `messageCount`, `superChatCount`, `membershipGiftCount`, `totalAmountByCurrency`, `chatComplete`.

Summarise what was found, cite the record URLs when present, and say how many items came back. Do not invent values for empty fields.