- Home
- Skills
- Workflow Automation
- Scrape.ly
Works with the AI Agents you already use
Scrape.ly
Ask your agent for web data and it finds one of 500+ ready-made Scrape.ly scrapers, runs it in the cloud and returns structured results: maps places, products, reviews, social posts, jobs.
Free
Scrape.ly
Example session with this skill installed
Scrape the first 10 search results for "mechanical keyboards" on Amazon and save them to a file called keyboards.json.
- Read your context and instructions
- Compiled the scrape ly
I have searched the Scrape.ly Store and identified the amazon-search-scraper Actor as the best fit. It has an "ok" health status and provides the price, rating, and product URL fields you need.
I have initiated the run with a limit of 10 items. The run completed successfully (Run ID: run_abc123xyz).
Scraped Results: Mechanical Keyboards
| Title | Price | Rating | URL |
|---|---|---|---|
| Keychron V3 Wired Mechanical Keyboard | $84.00 | 4.7 | https://www.amazon.com/dp/B0B1M9K |
| Logitech G Pro Mechanical Gaming Keyboard | $109.99 | 4.6 | https://www.amazon.com/dp/B07L9P |
| SteelSeries Apex Pro TKL | $174.99 | 4.8 | https://www.amazon.com/dp/B07TG |
| Razer BlackWidow V4 | $169.99 | 4.5 | https://www.amazon.com/dp/B0BV |
| Corsair K70 RGB MK.2 | $159.00 | 4.7 | https://www.amazon.com/dp/B07D |
The full data for all 10 items has been saved to keyboards.json.
Next steps
- Run
cat keyboards.jsonto view the full structured data. - If you need more results, I can fetch up to 100 items by increasing the limit.
- Access the full raw dataset at
https://api.scrape.ly/v2/datasets/ds_789ghi/items?format=json.
Connects securely to your tools. The creator never sees your data.
About this skill
Lets your coding agent collect real web data without writing a scraper. When you ask for data from a website ("get 50 dentists in Austin from Google Maps", "collect the latest reviews for this hotel"), the agent searches the Scrape.ly Store of 500+ ready-made scrapers, picks the best one, runs it in the cloud and reads back the results page by page.
What it does
- Searches the Scrape.ly Store for a scraper that fits the request
- Builds the input from the scraper's example and your request
- Tells you the price before large runs
- Runs the scraper and returns the first results, then fetches more on demand
- Saves big results to a file instead of flooding the conversation
Setup
- Create a free Scrape.ly account at https://scrape.ly ($5 of usage every month, no credit card).
- Create an API token in the Console (Settings > API & Integrations).
- Set it as the environment variable
SCRAPELY_TOKEN.
The helper script needs only Python 3.9+ and the standard library. Runs are billed to your own Scrape.ly account.
Requires SCRAPELY_TOKEN environment variable. Max synchronous wait time is 5 minutes. Cannot bypass private logins or authenticated sessions.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 5 days ago
- Free with an Agensi account
Requires
Permissions
Allowed Hosts
File Scopes