MrScraper
for LuumenAI
Check scraper health, then rerun or repair extraction jobs with approval
Connect MrScraper and Luumen can see how your scrapes are actually doing: success rates by domain and action, latency, recent results, and where your plan sits on tokens and concurrency. When a saved workflow stops matching its target site, the agent can heal it or rerun it against new URLs as an approved step. Authentication is by API key.
The MrScraper toolbox
11 tools: 5 read, 6 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadGet Account UsageReturn the connected MrScraper account's plan, token usage, concurrency allowance, and rate limits without exposing user identity or token details.
- ReadGet Scrape Status AnalyticsReturn aggregate scrape counts, success rate, request rate, latency, and status totals for a domain and action over a time range.
- ReadGet Scrape Analytics TimelineReturn time-series scrape activity and success metrics for a domain and action over a time range.
- ReadGet Scrape ResultRetrieve the current status and output for one accessible scrape result by ID.
- ReadList Scrape ResultsList scrape results for the connected account with filtering, sorting, and agent-controlled pagination.
- WriteBulk Rerun AI ScraperRun an existing General AI scraper configuration against multiple URLs in one request. Approval by default
- WriteBulk Rerun Manual ScraperRun an existing saved manual scraper workflow against multiple URLs in one request. Approval by default
- WriteCreate AI ScraperCreate and run a general, listing, or map AI scraper against a website. Approval by default
- WriteHeal Manual ScraperAsk MrScraper to repair an existing manual scraper workflow that no longer matches its target site. Approval by default
- WriteRerun AI ScraperRun an existing AI scraper configuration against a new URL, with optional map crawl controls. Approval by default
- WriteRerun Manual ScraperRun an existing saved manual scraper workflow against a new URL. Approval by default
One prompt, start to finish
What a governed MrScraper 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 — bulk rerun ai scraper, bulk rerun manual scraper, create ai scraper, heal manual scraper, and more — is shown as a plan and requires approval by default. 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 MrScraper — 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 MrScraper to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.