WebCrawlerAPI
for LuumenAI
Crawl sites, scrape pages, and watch vendor docs for changes from the terminal
Connect WebCrawlerAPI and Luumen can pull public web content into your operational work. Scrape a single page for a synchronous answer, check a crawl job's per-page results and observed costs, or review which monitored feeds detected changes overnight. Starting crawls, creating feeds, and changing feed state are previewed and approved first.
The WebCrawlerAPI toolbox
10 tools: 6 read, 4 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadGet Crawl JobGet a crawl job's status, configuration, per-page results, content URLs, errors, and observed costs.
- ReadGet FeedGet one feed's configuration, lifecycle status, and recent run history, including per-run crawl counts and cost.
- ReadGet Organization CostsReturn current spendable balance plus request count and USD usage for a date range.
- ReadList Feed ChangesReturn one page of detected feed changes as structured JSON, with an opaque continuation cursor for older pages.
- ReadList FeedsList active and paused feeds for the connected organization, newest first.
- ReadScrape PageScrape one web page synchronously and return requested content or structured extraction.
- WriteCreate CrawlStart a metered asynchronous crawl over a site and return its job ID. Approval by default
- WriteCreate FeedCreate a recurring website-change feed. Approval by default
- WriteDelete FeedPermanently cancel a feed so it cannot be resumed. Approval by default
- WriteSet Feed StatePause an active feed's future scheduled runs or resume a paused feed. Approval by default
One prompt, start to finish
What a governed WebCrawlerAPI run looks like inside Luumen.
Questions
Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
Read actions answer immediately. Anything that writes — create crawl, create feed, delete feed, set feed state — is shown as a plan and requires approval by default, including the 1 action classified as destructive. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.
You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.
Every call to WebCrawlerAPI — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Often connected alongside
All integrations
PostgreSQLQuery PostgreSQL state safely; maintenance held for approval.
MySQLQuery MySQL state safely; maintenance held for approval.
Microsoft SQL ServerQuery Microsoft SQL Server state safely; maintenance held for approval.Oracle DatabaseQuery Oracle Database state safely; maintenance held for approval.Put WebCrawlerAPI to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.