Simplescraper MCP for AI agents
Agents read Simplescraper MCP at once. Changes and sends are held for a person's approval by default.
About Simplescraper MCP
Simplescraper MCP lets agents create scraping recipes and extract structured live web data through an authenticated remote MCP server.
What an agent can do in Simplescraper MCP
Every Simplescraper MCP action is classed by the platform as a read, a change or a send. Reads run at once. Changes and sends are held for a person by default.
Runs at once (reads)
Looks things up in Simplescraper MCP without asking first. 8 actions.
- Extract markdownFetch one page and return its body as clean Markdown. Renders JavaScript before extraction. Returns markdown plus metadata (title, word count).
- Extract urlsDiscover all page URLs on a website by parsing its sitemap (and the sitemap index if present). Returns a deduplicated list of page URLs.
- Get latest resultsGet the most recent scraped results for a recipe. Returns the existing data from the last completed run without scraping again.
- Get recipeRetrieve full details of a specific scrape recipe: name, URL, creation date, last run time, and selectors.
- Get resultsFetch the scraped data from a specific run by results_id. Supports ordering (by index or timestamp) and pagination via limit and offset.
- Get results historyList previous scrape runs for a recipe. Each entry has results_id, scrape timestamp, and page count. Returns run metadata only, not the scraped data itself.
- List 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.
- Smart extractExtract specific named fields from one page using AI. Pass a comma-separated schema like 'product name, price, sku' and get those fields back as a structured object, plus the CSS selectors that matche
Held for approval by default (changes and sends)
Held for a person's approval by default. The approval is recorded and the action is sent once, never twice, with 10 seconds to undo. 5 actions.
- Create recipeCreate a new scrape recipe with a name, URL, and selectors.
- Run recipeRun a scrape recipe to extract fresh data from its configured URL. Supports async mode, source URL override, markdown extraction, and batch (crawler) mode.
- ScreenshotCapture a screenshot of a web page (1 credit per request). Returns JSON with a hosted screenshot URL by default. Supports full-page capture, custom viewport, format/quality, delays, and popup/ad hidin
- Update batch urlsAdd or replace the list of batch (crawler) URLs for a recipe. 'append' adds to the existing list, 'replace' overwrites it.
- Update recipeUpdate an existing scrape recipe's name, URL, or selectors. Supports 'replace' (default) or 'merge' modes for selector updates.
Changes wait in Needs you
Changes and sends in Simplescraper MCP are held for a person's approval by default. The approval is recorded, and the action is sent once, never twice, with 10 seconds to undo.
Related connectors
Simplescraper MCP questions
Can an agent change data in Simplescraper MCP on its own?
Not by default. Changes and sends in Simplescraper MCP are held for a person's approval. The approval is recorded, and the action is sent once, never twice, with 10 seconds to undo.
What can an agent read in Simplescraper MCP?
This connector lists 8 read actions. Reads run at once, without waiting for approval.
How does Simplescraper MCP connect?
It connects with dcr oauth. Connectors are built and maintained by third-party developers; availability is confirmed during scoping.