Give your agent a brand's Instagram handle. RouterGrowth scrapes its recent public posts and returns each one as a row: link, caption, date, likes, replies, views when the post is a video, and an is_video flag to split photos from video. No browser automation, no session cookies, no blocks to work around.
Ask your agent
Scrape the last 20 posts from these three luggage brands and tell me which formats get the most replies.
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 | likes | replies | views | is_video |
|---|---|---|---|---|---|
| 2026-10-10 | The details you notice when you need them. Padded laptop pockets. Trolley sleeves. Water-repellent fabric. Extra-comfortable straps. Though… | 165 | 3 | False | |
| 2026-10-14 | The perfect bag serves a million different moments. Explore the Signature Bag Collection. The Signature Tote in Dune Taupe | 136 | 4 | False | |
| 2026-10-13 | Your bag has a pocket problem. We’re trying to solve it.… | 200 | 4 | 4621 | True |
Five recent posts from Away's public account during a bag collection launch: photos with likes and replies, videos with views as well.
Step by step
Add the MCP server to Claude, Cursor or Claude Code. The scraping runs on RouterGrowth's side.
Give the handle or the profile URL and how many posts to read. social.posts returns them with their dates; the order is not strictly by date, so sort on created_at when it matters.
Ask for videos only, posts above a reply count, or captions that mention a product. The agent filters the rows it holds.
Pass a post URL to social.comments to read what people said on it.
Price
List prices on Instagram, 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 posts from these three luggage brands and tell me which formats get the most replies.
Take the Away post with the most replies this month and summarise its comments.
Find posts tagged #carryon this week and list the brands posting 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": "instagram", "handle": "away", "limit": 5}'curl -X POST https://api.routergrowth.com/v1/run \
-H "Authorization: Bearer $ROUTERGROWTH_API_KEY" \
-d '{"capability": "social.posts", "input": {"platform": "instagram", "handle": "away", "limit": 5}}'Worth knowing
The feed comes back mixed. is_video separates them, and views are filled on video posts only.
The scraper returns the post link and its caption, not the image or video file.
There is no scraper to patch when Instagram changes its markup. The router swaps providers behind the same fields.
FAQ
Video posts in the feed come back with is_video set to true and a view count. The output does not label a separate reel type.
Set the limit you need. Start small, check the rows, then raise it for the full history you want.
No. Only public posts are read and no login is used.
Ask the agent for a CSV or a table, or save them to a workspace table to enrich later.
More on Instagram
Reading this as an agent? This page as markdown: /tools/instagram/posts-scraper.md
Connect your agent once. The first calls run on the $1 that comes with signup.