scrapewright
URL-to-rows scraper that has a model write a parser once and replays it free
- Pricing
- Freemium
- Platforms
- API, CLI, Web
- Runs
- Locally or Remotely
- Version
- 1.0.3
- Listing updated
- 1 day ago
About scrapewright
scrapewright is a freemium MCP server for web search and scraping. It can run locally on your machine or as a hosted remote server.
scrapewright treats the language model as a compiler rather than a runtime. It detects the platform behind a URL, reads Shopify and WooCommerce stores straight from their public catalogue data, and only calls a model for sites on no known platform, once, to write a recipe of CSS selectors that is cached and replayed with plain parsing.
Results normalise to one product shape with title, price, brand and images. The README shows catalogue, single-page and whole-store crawl modes, a CLI, a Python library and an MCP server, available over stdio from PyPI or as a hosted Streamable HTTP endpoint with an API key. Only custom sites need an Anthropic key, and the robots.txt setting defaults to obeying the file.
Hosted billing is per row delivered with no subscription. Every account gets 1,000 free rows a month, JavaScript-only pages cost 5 and compiling a new site costs 300.
Install
Run in a terminal
claude mcp add --transport http scrapewright https://scrapewright.app/mcpAdd to Settings → Connectors → Add custom connector
https://scrapewright.app/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"scrapewright": {
"url": "https://scrapewright.app/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"scrapewright": {
"type": "http",
"url": "https://scrapewright.app/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"scrapewright": {
"serverUrl": "https://scrapewright.app/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"scrapewright": {
"type": "http",
"url": "https://scrapewright.app/mcp"
}
}
}Configuration
ANTHROPIC_API_KEYOnly needed for sites on no known platform, where a recipe has to be written once. Shopify and WooCommerce stores work without it.SCRAPEWRIGHT_CACHEWhere compiled recipes are kept. Point it at durable storage, or every restart pays to work the same sites out again. Defaults to ~/.scrapewright/recipes.jsonSCRAPEWRIGHT_OBEY_ROBOTSSet to 0 to ignore robots.txt. Only reasonable on sites you own or have written permission for; the default is to obey.
What it does
- Platform detection
- Recognises Shopify, WooCommerce and others and reads their catalogues directly.
- One-time recipe compile
- A model writes CSS selectors once per site.
- Free replays
- Cached recipes parse later pages without a model.
- Crawl mode
- Walks a whole store from a listing URL.
- Export formats
- Writes CSV, XLSX or JSONL.
- Robots.txt by default
- Obeys robots.txt unless you switch it off.
Good for
- Collect a competitor's product catalogue
- Build a price feed from a custom shop
- Scrape a shop for catalogue enrichment without per-page model costs
- Give an agent a tool to turn a URL into product rows
Pricing
Freemium
1,000 free rows a month; pay per row after that; no subscription
Prices change. Check scrapewright.app before you buy.
scrapewright FAQ
How is it billed?
One credit per row delivered, no subscription and credits do not expire. Each account gets 1,000 free rows a month.
Do I need an API key for the model?
Only for sites on no known platform, where a recipe must be written once; Shopify and WooCommerce work without it.
Does it obey robots.txt?
Yes by default, via the SCRAPEWRIGHT_OBEY_ROBOTS setting.
Where are recipes stored?
In a cache file, by default ~/.scrapewright/recipes.json.
Is scrapewright free?
scrapewright has a free plan, with paid plans for more usage or features.
How do I add scrapewright to Claude Code?
Run this command in your terminal: claude mcp add --transport http scrapewright https://scrapewright.app/mcp
What are the best alternatives to scrapewright?
The closest alternatives to scrapewright are Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search, O'So MCP Server for PrestaShop and NeuralVerge.
Alternatives to scrapewright

Scrapling MCP Server
MCP serverMCP server for AI clients to scrape sites with HTTP and stealth browser sessions
Runs locally- 17 tools
- Open source
- 104K GitHub stars
- Web search and scraping

Firecrawl MCP Server
MCP serverMCP server that lets AI agents search, scrape and interact with web pages
- 3 tools
- Remote
- Freemium
- 7.8K GitHub stars
- Web search and scraping

SearXNG Search
MCP serverMCP server for web search and page reading through a SearXNG instance
Runs locally- 3 tools
- Open source
- 1.4K GitHub stars
- Web search and scraping
O'So MCP Server for PrestaShop
MCP serverLet Claude, ChatGPT or Cursor manage a PrestaShop shop with per-employee permissions
Not checked yet- Remote
- Open source
- 2 GitHub stars
- E-commerce

NeuralVerge
MCP serverStructured, source-tagged business and people data from 300+ sources for agents
- 200 tools
- Remote
- Free trial
- 1 GitHub star
- Web search and scraping

AI-Powered directory
MCP serverSearch AI tools, agents and MCP servers and get install configs from inside your AI assistant.
- 4 tools
- Remote
- Free
- Developer tools