Webscraper io for AI agents
Web Scraper.io runs cloud-based scraping jobs from configured sitemaps, used by data teams that extract structured data from websites on a schedule. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Webscraper io.
Get scraping jobs
Pull the status and results of scraping jobs as a read-only check.
Create a sitemap
Define a new sitemap describing which pages and fields to scrape.
Confirm before deleting a sitemap
Check with the user before deleting a sitemap, since its scheduled jobs stop running.
10 Webscraper io actions, graded by risk.
Every Webscraper io action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
5Look things up. Allowed by default.
- webscraper_io.get_sitemapGet Sitemap
- webscraper_io.get_sitemapsGet Sitemaps
- webscraper_io.get_account_infoGet Account Info
- webscraper_io.get_scraping_jobsGet Scraping Jobs
- webscraper_io.get_sitemap_schedulerGet Sitemap Scheduler
write
3Create and change things. Allow, or ask the user first.
- webscraper_io.create_sitemapCreate Sitemap
- webscraper_io.update_sitemapUpdate Sitemap
- webscraper_io.enable_sitemap_schedulerEnable Sitemap Scheduler
destructive
2Delete, cancel or archive. Ask first, or deny outright.
- webscraper_io.delete_sitemapDelete Sitemap
- webscraper_io.disable_sitemap_schedulerDisable Sitemap Scheduler
Webscraper io in three steps.
- 01Your users connect Webscraper ioThey add their Webscraper io api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Sitemap” can wait for the user, and “delete Sitemap” can be denied outright.
- 03Any agent can actYour agent calls Webscraper io through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('webscraper_io', { read: 'allow', write: 'ask', // create_sitemap destructive: 'deny', // delete_sitemap }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Webscraper io connects.
Users add their Webscraper io api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Webscraper io connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Webscraper io from any agent.
Webscraper io and Arc0, answered.
Can I use Webscraper io with Claude, ChatGPT or Cursor?
Yes. Connect Webscraper io to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Webscraper io actions you allow.
How do users connect Webscraper io?
Users add their Webscraper io api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Webscraper io actions can my agent take?
10 in total: 5 read, 3 write and 2 destructive, such as “create Sitemap”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Webscraper io?
Yes. Actions like “delete Sitemap” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call Webscraper io too?
Yes. The same Webscraper io connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Webscraper io into your agent.
Your users connect Webscraper io once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan