Operated by Sourcelane✓ verified
Scrape the replies under TikTok comments: every reply's text, likes, date and author, linked to its parent comment. Paste video links or shared comment links.
A scraper for TikTok reply threads that extracts every reply under specified videos or a shared comment link and returns structured, reply-level records: reply text, reaction counts, timestamps, detected language, and whether the video creator liked the reply; reply author metadata (username, display name, user identifier, profile URL, avatar, verification flag); thread context indicating if the item answers another reply and the parent reply identifier; parent comment content and metadata (identifier, text, author, likes, date, total reply count); and associated video identifier and URL. The connector navigates top-level comments, loads reply pages for threads, and links each reply to its parent comment. It operates without requiring a login and is intended for downstream analysis and monitoring workflows.
Verified Oct 25, 10:11 PM
$0.001
per reply
Up to 100 per call. Only pay for results returned; failed calls are refunded.
Audience and sentiment research
Capture discussion in reply threads rather than only top-level comments
Lead generation
Find users asking purchase or price questions under product videos
Community management
Export conversations under videos to respond to missed questions
Brand monitoring
Observe reactions to complaints or mentions of a brand in reply threads
Content ideas
Mine heated debates and frequently asked follow-up questions
TikTok video URLs, short links, video IDs, or shared comment links.
Optional settings
| Window | Uptime | Success rate | p50 | p95 | Calls |
|---|---|---|---|---|---|
| 24h | — | — | — | — | 0 |
| 7d | — | — | — | — | 0 |
| 30d | — | — | — | — | 0 |
Call it through Sourcelane's gateway or MCP server. We run the connector, apply your agent's spend guardrails, and bill only the results returned.
Call it via Sourcelane
curl -X POST https://api.usesourcelane.com/v1/call \
-H "Authorization: Bearer sl_live_your_agent_key" \
-H "Content-Type: application/json" \
-d '{"listing":"tiktok-comment-replies-scraper","params":{"videoUrls":["https://www.tiktok.com/@khaby.lame/video/7689510970292489502"],"maxItems":5},"maxResults":10}'Request params
| Field | Type | Required | Description |
|---|---|---|---|
videoUrls | array | required | TikTok video URLs, short links (vm.tiktok.com), video IDs, or shared comment links (to scrape one comment's replies only). |
maxCommentsPerVideo | integer | optional | How many top-level comments to scan per video, most relevant first. Replies are scraped for each comment that has them. 0 = all comments. |
maxRepliesPerComment | integer | optional | Stop after this many replies in one comment thread. 0 = all replies. |
minReplies | integer | optional | Skip comments with fewer replies than this. Raise it to focus on the busiest conversations. |
maxItems | integer | optional | Stop the run after this many replies. 0 = no limit. Capped at 100 per call. |
Each result contains
| Field | Type | Description |
|---|---|---|
replyId | string | — |
text | string | Reply |
createdAt | string | Posted |
likes | integer | Likes |
likedByCreator | boolean | — |
language | string | — |
isReplyToReply | boolean | — |
repliedToReplyId | null | — |
authorUsername | string | Author |
authorNickname | string | — |
authorUserId | string | — |
authorSecUid | string | — |
authorProfileUrl | string | — |
authorAvatarUrl | string | — |
authorVerified | boolean | — |
parentCommentId | string | — |
parentCommentText | string | Parent comment |
parentCommentAuthor | string | Parent author |
parentCommentLikes | integer | — |
parentCommentCreatedAt | string | — |
parentReplyCount | integer | — |
videoId | string | — |
videoUrl | string | Video |
scrapedAt | string | — |
Pick your tool and connect in under a minute. Then just ask — for example: “What are the top 25 TikTok videos for 'protein coffee' this week, and what hooks do they use?”
Connect Claude
Web, desktop and mobile. One click, then confirm.
Adds the Sourcelane MCP server with your key as a header.
claude mcp add --transport http sourcelane https://api.usesourcelane.com/mcp \
--header "Authorization: Bearer sl_live_your_agent_key"Alternative to the connector URL: add to claude_desktop_config.json, then restart Claude.
{
"mcpServers": {
"sourcelane": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://api.usesourcelane.com/mcp",
"--header",
"Authorization:${AUTH_HEADER}"
],
"env": {
"AUTH_HEADER": "Bearer sl_live_your_agent_key"
}
}
}
}Add to ~/.cursor/mcp.json (or Windsurf's mcp_config.json).
{
"mcpServers": {
"sourcelane": {
"url": "https://api.usesourcelane.com/mcp",
"headers": {
"Authorization": "Bearer sl_live_your_agent_key"
}
}
}
}Save as .vscode/mcp.json. VS Code prompts for your key once.
{
"servers": {
"sourcelane": {
"type": "http",
"url": "https://api.usesourcelane.com/mcp",
"headers": {
"Authorization": "Bearer ${input:sourcelane-key}"
}
}
},
"inputs": [
{
"type": "promptString",
"id": "sourcelane-key",
"description": "Sourcelane agent key",
"password": true
}
]
}Create a GPT → Actions → Import from URL, then Authentication: API Key, Bearer.
https://usesourcelane.com/openapi.jsonOne POST. Pass maxResults to cap cost.
curl -X POST https://api.usesourcelane.com/v1/call \
-H "Authorization: Bearer sl_live_your_agent_key" \
-H "Content-Type: application/json" \
-d '{"listing":"tiktok-comment-replies-scraper","params":{"videoUrls":["https://www.tiktok.com/@khaby.lame/video/7689510970292489502"],"maxItems":5},"maxResults":10}'Wrap the REST call as a tool, or point an MCP client at the endpoint.
import requests
res = requests.post(
"https://api.usesourcelane.com/v1/call",
headers={"Authorization": "Bearer sl_live_your_agent_key"},
json={
"listing": "tiktok-comment-replies-scraper",
"params": {"videoUrls":["https://www.tiktok.com/@khaby.lame/video/7689510970292489502"],"maxItems":5},
"maxResults": 10,
},
timeout=300,
)
body = res.json()
print(body["receipt"]["chargedMicros"], "micro-USD for", body["receipt"]["results"], "results")
print(body["data"])—
0 reviews
Leave a review
Loading reviews…