Simplescraper MCP
for LuumenAI

Build scrape recipes and pull structured web data, as approved steps

Point Luumen at a page and get back clean Markdown, a sitemap's worth of URLs, or the latest rows from a saved recipe. Every Simplescraper call is a write here, so by default it is previewed, approved, and logged before it runs. Connect over the remote MCP server with OAuth dynamic client registration.

The Simplescraper MCP toolbox

13 tools: 0 read, 13 write. Reads answer instantly. Writes require approval by default. Everything is logged.

  • WriteCreate recipeCreate a new scrape recipe with a name, URL, and selectors. Approval by default
  • WriteExtract markdownFetch one page and return its body as clean Markdown. Approval by default
  • WriteExtract urlsDiscover all page URLs on a website by parsing its sitemap (and the sitemap index if present). Approval by default
  • WriteGet latest resultsGet the most recent scraped results for a recipe. Approval by default
  • WriteGet recipeRetrieve full details of a specific scrape recipe: name, URL, creation date, last run time, and selectors. Approval by default
  • WriteGet resultsFetch the scraped data from a specific run by results_id. Approval by default
  • WriteGet results historyList previous scrape runs for a recipe. Approval by default
  • WriteList recipesList the user's scrape recipes, with optional filters by domain, name keyword, or recent activity, and sorting by creation date, last-run, or name. Approval by default
  • WriteRun recipeRun a scrape recipe to extract fresh data from its configured URL. Approval by default
  • WriteScreenshotCapture a screenshot of a web page (1 credit per request). Approval by default
  • WriteSmart extractExtract specific named fields from one page using AI. Approval by default
  • WriteUpdate batch urlsAdd or replace the list of batch (crawler) URLs for a recipe. Approval by default
  • WriteUpdate recipeUpdate an existing scrape recipe's name, URL, or selectors. Approval by default

Questions

How does LuumenAI connect to Simplescraper MCP?

Authorize once with OAuth 2.0. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

Can LuumenAI change things in Simplescraper MCP on its own?

Read actions answer immediately. Anything that writes — create recipe, extract markdown, extract urls, get latest results, 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.

Who gets access to the integration?

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.

Is there an audit trail?

Every call to Simplescraper MCP — 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.

Put Simplescraper MCP to work with Luumen

Connect in minutes. Every action scoped, approved, and audited from day one.