Name a TikTok account. RouterGrowth scrapes its recent public videos and returns one row per video: URL, caption, date, views, likes, replies and reposts. It reads the data, not the media: there is no video file and no transcript, and nothing to maintain on your side.
Ask your agent
Scrape the last 20 videos from Olipop and two rival soda brands and compare views per video.
Connect RouterGrowth once, then ask in plain words. New workspaces start with $1 of credit. Get a key or read the setup guide.
A real run
One call to social.posts (social posts & content), run through RouterGrowth on October 19, 2026. These are the first rows it returned; fields that name a person are masked.
| created_at | text | views | likes | replies |
|---|---|---|---|---|
| 2026-10-14 | Secret stash exposed 🤫 | 2244 | 114 | 35 |
| 2026-10-17 | TAKE ME THERE | 1188 | 108 | 28 |
| 2026-10-16 | Harry's #1 fan club 🪩🫧😏 | 1244 | 73 | 22 |
The five latest Olipop videos, one a day: short captions, around 1,200 to 2,200 views each.
Step by step
Add it to your agent over MCP. The scraping runs on RouterGrowth's providers.
Give the handle or profile URL and a limit. social.posts returns the recent videos.
Ask for views per video, the posting rhythm, or which captions get more replies.
Pass its URL to social.comments to read the replies under it.
Price
List prices on TikTok, read from the catalog when this page was built. The exact figure is quoted before every run, and a monthly plan lowers it.
In practice
You describe the job; the agent picks the calls, shows the price and runs them.
Scrape the last 20 videos from Olipop and two rival soda brands and compare views per video.
Find the Olipop video with the most replies this month and summarise what people said under it.
Connect
One MCP server for Claude, ChatGPT, Claude Code, Codex and Cursor, or the same call over the CLI and REST with the input above.
claude mcp add --transport http routergrowth https://api.routergrowth.com/mcp
npm install -g routergrowth && routergrowth setup
routergrowth run -c social.posts -i '{"platform": "tiktok", "handle": "drinkolipop", "limit": 5}'curl -X POST https://api.routergrowth.com/v1/run \
-H "Authorization: Bearer $ROUTERGROWTH_API_KEY" \
-d '{"capability": "social.posts", "input": {"platform": "tiktok", "handle": "drinkolipop", "limit": 5}}'Worth knowing
Each row has the video URL. The scraper does not download the MP4.
Brand captions are often a few words, as in this run. The view and reply counts carry more of the signal.
Providers and fallbacks change on the RouterGrowth side; the fields you parse stay the same.
FAQ
No. It returns the video page URL and its data, not the media file.
No. The text field is the caption.
As many recent videos as the limit asks for, from the public profile.
No. Fetching and retries run on the RouterGrowth side.
More on TikTok
Reading this as an agent? This page as markdown: /tools/tiktok/video-scraper.md
Connect your agent once. The first calls run on the $1 that comes with signup.