Simplescraper extracts structured data from websites using AI, discovers page URLs from sitemaps, converts web pages to Markdown, captures screenshots, and automates reusable scraping recipes for bulk data collection and monitoring.
Hermes is Nous Research's command-line agent. MCP servers are declared in its YAML config and reloaded without a restart.
This guide connects Simplescraper MCP to Hermes through MewCP, so Hermes can use Simplescraper MCP's 13 tools, like get_latest_results, get_results_history and list_recipes, without your Simplescraper MCP credentials ever reaching the app.
Simplescraper MCP signs in through managed OAuth. MewCP stores the token encrypted, refreshes it before it expires and injects it only at call time. Your agent never holds it, so it can never leak it.
More apps
Crawl websites and extract clean structured data optimized for AI applications and automation. Collect content from the web at scale while maintaining high-quality outputs.
Extract structured data from websites and public web pages. Fetch content, parse information and transform online data into formats that can be consumed by applications, agents and workflows.
TinyFish MCP for running AI-driven browser automation tasks, deep web research, persistent browser login profiles, remote CDP browser sessions, and agentic wallet payments.
Scrape, extract, and understand the web, plus identify any company from a domain, email, name, or transaction string. This MCP server exposes Context.dev's API for web scraping in multiple formats (raw HTML, Markdown, screenshots, images, sitemaps, and web search), schema-driven structured data extraction, design-system extraction (styleguides and fonts), and brand intelligence lookups. It's built for AI agents that read, summarize, or monitor web content, for enriching CRM, KYC, or fintech pipelines with company and brand data, and for extracting a competitor's design system or structured product and pricing data at scale.
Other clients
Simplescraper MCP works the same way in every client below. Pick yours for its own guide.
Free to start.
Scope access to the exact Simplescraper MCP tools and accounts you allow, work and personal side by side. Anything outside that scope is refused at call time, even when the model asks for it.
Each call is logged: what ran, on which account, and whether it worked. Failures come back structured, so the agent knows whether to retry instead of guessing.
Every app sits behind one secure MCP URL, and there is no server for you to deploy or keep running. Add an integration in the dashboard and it is live on the next call, with no config to change and no new credentials to wire up. Tools load only when a task needs them, so your agent stays fast and focused however many apps you connect.
Edit config.yaml in your Hermes config directory (~/.hermes).
Put this under the top-level "mcp_servers:" key.
Run /reload-mcp in Hermes, or start a fresh session. Sign in when the browser window opens.
Start a new chat and ask: "List the tools you can use from MewCP." You should see your connected apps.
Get the most recent scraped results for a recipe. Returns the existing data from the last completed run without scraping again.
List 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 the user's scrape recipes, with optional filters by domain, name keyword, or recent activity, and sorting by creation date, last-run, or name.
Run a scrape recipe to extract fresh data from its configured URL. Supports async mode, source URL override, markdown extraction, and batch (crawler) mode.
Create a new scrape recipe with a name, URL, and selectors.
Retrieve full details of a specific scrape recipe: name, URL, creation date, last run time, and selectors.
Update an existing scrape recipe's name, URL, or selectors. Supports 'replace' (default) or 'merge' modes for selector updates.
Fetch the scraped data from a specific run by results_id. Supports ordering (by index or timestamp) and pagination via limit and offset.
Extract 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 matched them.
Discover all page URLs on a website by parsing its sitemap (and the sitemap index if present). Returns a deduplicated list of page URLs.
Fetch one page and return its body as clean Markdown. Renders JavaScript before extraction. Returns markdown plus metadata (title, word count).
Add or replace the list of batch (crawler) URLs for a recipe. 'append' adds to the existing list, 'replace' overwrites it.
Capture 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 hiding. Defaults output to 'url' so the response stays small; 'binary' returns raw image bytes and is not suited to an MCP text response.
