Scraper MCP Server

MCP server for web scraping — extract clean markdown, links, metadata from any URL

Local serverstdio

What is the Scraper MCP server?

Scraper MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. MCP server for web scraping — extract clean markdown, links, metadata from any URL.

What you get

Extract clean, readable content from any URL. Returns markdown text, links, and metadata. No API keys, no config. A free alternative to Firecrawl for scraping docs, blogs, and articles.

Setting it up

Installation goes through your MCP client rather than a global install: point it at mcp-server-scraper on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

What the assistant can call

Once Scraper is connected, these are the calls the assistant has available:

  • scrape_url — Extract clean text content from a URL (Readability-powered)
  • extract_links — Get all links with href and anchor text
  • extract_metadata — Get title, description, OG tags, canonical, favicon
  • search_page — Search for a query string within the page, return matching lines
  • scrape_multiple — Batch scrape multiple URLs, get title + excerpt per URL
  • Cursor — The Cursor tool exposed by this server

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the scraper mcp server does with a few real requests.

Choosing this one

This sits in the search and retrieval group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Scraper's toolset — scrape_url, extract_links, extract_metadata and 3 more — is a fair guide to whether it matches your workflow. It is maintained by ofershap; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Scraper's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Available tools

ToolWhat it does
scrape_urlExtract clean text content from a URL (Readability-powered)
extract_linksGet all links with href and anchor text
extract_metadataGet title, description, OG tags, canonical, favicon
search_pageSearch for a query string within the page, return matching lines
scrape_multipleBatch scrape multiple URLs, get title + excerpt per URL
CursorThe Cursor tool exposed by this server.

How to install the Scraper MCP server

{
  "mcpServers": {
    "scraper": {
      "command": "npx",
      "args": ["-y", "mcp-server-scraper"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Scraper to scrape url.
  • Use Scraper to extract links.
  • Use Scraper to extract metadata.

Frequently asked questions

It is a free, open-source alternative that performs the same core task for static server-rendered pages without needing a paid API key.