scrapewright MCP Server

by ozymandias-owens-2 Your server? Claim it

answering

scrapewright is answering right now. Last checked 6 min ago. 93 installs a week from pypi. It exposes 5 tools. Last commit 1 Nov 2026.

Give it a URL, get structured rows. A model writes the parser once; replays are free.

Installs per day peak 77 · avg 26 · -31% w/w

a month agotoday

Uptime history 43 days of history · worst day 91%

43 days agonow

100.0%

Uptime 24h

92 of 92 checks

Tools

read from the server

177 ms

Response time

average over 24h

Installs / week

npm and PyPI

What changed 5

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 29 September 2026. No other catalogue keeps this.

1 Oct a tool description was rewritten extract_page

1 Oct a tool changed the parameters it asks for extract_page

30 Sep a tool description was rewritten crawl_site

30 Sep a tool changed the parameters it asks for crawl_site

29 Sep a tool changed version

What the code does

We read the source, 21 h ago · tools taken from the live server · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Page executes code built at runtime [пакет] scrapewright/service/static/account.html:138, [пакет] scrapewright/service/static/index.html:411, scrapewright/service/static/account.html:206 и ещё 1

    (where || status).innerHTML = html ? '<div class="msg ' + cls + '">' + html + '</div>' : '';

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 6 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add scrapewright --transport http https://scrapewright.app/mcp

Settings → Connectors → Add custom connector, then paste this address

https://scrapewright.app/mcp

~/.codex/config.toml

[mcp_servers.scrapewright]
url = "https://scrapewright.app/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "scrapewright": {
      "url": "https://scrapewright.app/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "scrapewright": {
      "type": "http",
      "url": "https://scrapewright.app/mcp"
    }
  }
}

Available tools 5

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

crawl

crawl_site

Walk a site and extract every item. Waits up to four minutes; a longer crawl returns a job_id to pass to crawl_status. `mode` picks how the items are found. "rows" (the default) reads every card on the listing itself and follows its pagination -- right for search results, categories and tables. "links" follows each card into its own page, for sites where an item has one. "like" starts from one example item page, given as `like_page`, and finds every other page shaped like it; pass `listing_url` as well when you know the stock or results page, because inferring it is the part that fails.

crawl_status

Fetch a crawl that outlived its call.

account

account

Credits left and this month's usage for the key in use.

detect

detect_site

Report what platform a site runs on and which strategy to use. Cheap; call it before a large job.

extract

extract_page

Extract structured data from ONE page. ``fields`` declares your own schema, e.g. ["title", "salary:number", "tags:list"]; omit it for the product schema. First call on a new site compiles a recipe (300 credits); later calls replay it for 1 credit per row. A site nobody could read is remembered for a week and answered without calling the model, so re-reading a dead page costs nothing. `retry` asks anyway.

Endpoints

URL	Transport	State	Latency	Checked
https://scrapewright.app/mcp	streamable-http	answering	164 ms	6 min ago

Alternatives to scrapewright

same job, measured the same way

Perpage MCP Server

by cal-dev-tech

Give AI agents clean, LLM-ready web data — scrape any URL to markdown or extract structured JSON.

47 installs/wk local only

Olostep MCP Server

by olostep

Live web search, scraping and crawling API for AI. Get structured, LLM-ready data from any site.

1 489 installs/wk answering

PageMap

by retio-ai

Structured web intelligence for AI agents. 5x fewer tokens than Playwright/Firecrawl, 84.7% accuracy

54 installs/wk local only

Firecrawl

by mcparmory

Scrape, crawl, and extract structured data from websites at scale

209 installs/wk local only

Scraperapi

by pipeworx-io

ScraperAPI MCP — wraps ScraperAPI (scraperapi.com), a proxy-based web scraper with structured-data…

197 installs/wk 48 tools answering

Writ Cloud

by usewrit

Read, crawl and act on websites, signed in as the user, and turn any site into an API.

45 installs/wk 41 tools answering

Parser Club

by parser

Telegram/VK audience scraping, marketplaces, Russian government registers. Free open dataset.

6 tools answering

Serp Data Scraper

by jojapi

SERP data scraper: Scrape Search Results and get all the data you need. On the JoJ API marketplace.

1 tools answering

scrapewright — questions

Answers built from our own checks of this server.

What can scrapewright do?

It exposes 5 tools, read directly from the server on our last check. Among them: account, crawl_site, crawl_status, detect_site, extract_page. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is scrapewright working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 177 ms. The bar chart above shows every period we have measured.

How do I connect scrapewright?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does scrapewright need an API key?

No. scrapewright completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 5 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is scrapewright?

It answers our handshake in 177 ms on average, which is faster than 77% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.

How many people use scrapewright?

The pypi package scrapewright was installed 93 times in the last week. Week over week that is -31%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is scrapewright open source?

The code is open source: it is published under the MIT licence, written in Python and 1 stars on GitHub. The licence covers the code in the repository, not the hosted service at scrapewright.app, which runs on its operator's own terms.