TikTok Comment & Reply Thread Extractor: MCP config, n8n workflow and API

{
  "postUrls": [
    "https://www.tiktok.com/@khaby.lame/video/7574844184952081686"
  ],
  "maxVideosPerProfile": 5,
  "maxCommentsPerPost": 5,
  "includeReplies": true,
  "maxRepliesPerComment": 5,
  "maxItems": 0,
  "minLikes": 0,
  "includeVideoMetadata": false,
  "includeCommenterDetails": false,
  "includeCommenterStats": false,
  "maxCommenterLookups": 100,
  "deepWalk": false
}

---
name: tiktok-comment-and-reply-thread-extractor
description: "One record per TikTok comment or reply, with text, like/reply counts, pinned/hearted flags, reply-thread links, and commenter details. Runs the Apify Actor vexaloom-labs/tiktok-comment-and-reply-thread-extractor. Use when the user needs TikTok data with fields such as rowType, commentId, postId, text, createdAt, likeCount 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: "vexaloom-labs/tiktok-comment-and-reply-thread-extractor"
  store-url: "https://apify.com/vexaloom-labs/tiktok-comment-and-reply-thread-extractor"
---

# TikTok Comment & Reply Thread Extractor

Use this skill to fetch TikTok data with the Apify Actor `vexaloom-labs/tiktok-comment-and-reply-thread-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 |
| --- | --- | --- |
| `postUrls` | array | TikTok video or photo URLs to scrape comments from (e.g. https://www.tiktok.com/@user/video/123...). |
| `maxVideosPerProfile` | integer | How many of each profile's newest videos to scrape comments from. |
| `maxCommentsPerPost` | integer | Maximum number of rows per video, counting replies when 'Include replies' is on. The actor walks the comment section as deep as TikTok serves it. |
| `includeReplies` | boolean | Fetch the reply thread under each root comment and emit each reply as its own row right after its parent. |
| `maxRepliesPerComment` | integer | Cap the replies fetched for any single root comment. Set to 0 for all replies (still bounded by 'Max comment rows per video'). |
| `maxItems` | integer | Global cap on the number of rows in the run (comments + replies). Set to 0 for no global cap. |
| `minLikes` | integer | Only keep comments and replies with at least this many likes. Comments below the threshold are skipped before their replies are fetched. |
| `includeVideoMetadata` | boolean | Add a 'video' object (caption, author, view/like/comment counts) to every row. |
| `includeCommenterDetails` | boolean | Add the commenter's region code and bio to user.region / user.bio, matched by comment ID from TikTok's app-style view of the page. |
| `includeCommenterStats` | boolean | Add exact follower, following, heart and video counts to user.* for every commenter. Each commenter's public profile is looked up once; private or banned accounts are omitted. |
| `maxCommenterLookups` | integer | Cap on how many commenters are enriched when 'Include commenter follower counts' is on. Set to 0 for no cap. |
| `deepWalk` | boolean | Read TikTok's app-style view of the comment list, which reaches far more comments on many videos, and restore image/sticker data from the standard view per comment. Off keeps the standard walk. |

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

```json
{
  "postUrls": [
    "https://www.tiktok.com/@khaby.lame/video/7574844184952081686"
  ],
  "maxVideosPerProfile": 5,
  "maxCommentsPerPost": 5,
  "includeReplies": true,
  "maxRepliesPerComment": 5,
  "maxItems": 0,
  "minLikes": 0,
  "includeVideoMetadata": false,
  "includeCommenterDetails": false,
  "includeCommenterStats": false,
  "maxCommenterLookups": 100,
  "deepWalk": false
}
```

## Run

```bash
curl -sS -X POST "https://api.apify.com/v2/acts/vexaloom-labs~tiktok-comment-and-reply-thread-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/vexaloom-labs~tiktok-comment-and-reply-thread-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: `rowType`, `commentId`, `postId`, `text`, `createdAt`, `likeCount`, `replyCount`, `isReply`, `replyToCommentId`, `user`, `replyToReplyId`, `replyToUsername`, `postUrl`, `video`.

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