Crawlbase
for LuumenAI
Crawl pages, read stored results, and check usage from the terminal
Connect Crawlbase and Luumen can answer questions about your crawling setup without you opening a browser. Check current Crawling API usage, count the pages in Cloud Storage, list request IDs, and pull back a stored page by ID or original URL. When a page needs to be fetched fresh, the crawl runs as a previewed step you approve first. Authentication is by API key.
The Crawlbase toolbox
8 tools: 6 read, 2 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadGenerate User AgentsGenerate one to ten realistic randomized User-Agent strings for a selected device class.
- ReadGet Crawling UsageReturn current Crawling API usage and optionally previous-month statistics for the connected Crawlbase account.
- ReadGet Storage CountReturn the number of pages currently held in Crawlbase Cloud Storage.
- ReadGet Stored PageRetrieve the latest Crawlbase Cloud Storage page by exactly one request ID or original URL.
- ReadGet Stored PagesRetrieve up to 100 Crawlbase Cloud Storage pages by request ID without deleting them.
- ReadList Stored Page IDsReturn one page of Crawlbase Cloud Storage request IDs and a short-lived continuation cursor.
- WriteCrawl URLFetch a public HTTP or HTTPS URL through Crawlbase using the connected Normal token and return its content with separate target and Crawlbase statuses. Approval by default
- WriteDelete Stored PagesIrreversibly delete explicitly selected pages from Crawlbase Cloud Storage by request ID and return each page's deletion outcome. Approval by default
One prompt, start to finish
What a governed Crawlbase 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 — crawl url, delete stored pages — 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 Crawlbase — 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 Crawlbase to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.