Scraper MCP Server

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. Its 5 documented tools cover scrape, extract. It runs locally over stdio via the published package.

People connecting web scraping tools to Claude, Cursor, VS Code, or another MCP client. The project is written in TypeScript.

VERIFIED ACTIVE

LAST COMMIT 2026-08-10 · ★ 5 · #32 OF 78 MAINTAINED WEB SCRAPING · VERIFIED 2026-08-25

MIT · TypeScript servers · how we verify → /methodology

01 · Install Scraper

before you install - you'll need

The README does not document required environment variables for a basic install.

Claude Code

claude mcp add ofershap-mcp-server-scraper -- npx -y mcp-server-scraper

Claude Desktop / Cursor / VS Code - add to config

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

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

npm package mcp-server-scraper - unscoped; check the name against the project README before installing

registry namespace io.github.ofershap is GitHub-verified and matches the repo owner

03 · What Scraper can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can extract clean text content from a URL (Readability-powered), get all links with href and anchor text, get title, description, OG tags, canonical, favicon, and search for a query string within the page, return matching lines.

Capability map

Tools grouped from the project's README - what Scraper lets an agent do.

Scrape

2 tools - e.g. Extract clean text content from a URL (Readability-powered); Batch scrape multiple URLs, get title + excerpt per URL

scrape_url · scrape_multiple

Extract

2 tools - e.g. Get all links with href and anchor text; Get title, description, OG tags, canonical, favicon

extract_links · extract_metadata

read & search

1 tool - e.g. Search for a query string within the page, return matching lines

search_page

04 · Who maintains Scraper

scraper is maintained by ofershap. We track 15 MCP servers from ofershap - 15 actively maintained, 92 combined GitHub stars, oldest repo from Feb 2026. Full record: all servers from ofershap.

05 · Facts

repository: github.com/ofershap/mcp-server-scraper
category: web scraping - ranked #32 of 78 actively-maintained web scraping servers as of 2026-08-25.
registry: io.github.ofershap/scraper (active, first published 2026-03-10)
packages: npm:mcp-server-scraper

06 · Scraper FAQ

Is Scraper still maintained?

Yes - as of 2026-08-25, its last commit was 2026-08-10. We re-verify nightly.

What can Scraper do?

How do I install Scraper?

Run `npx -y mcp-server-scraper`. The README does not document required environment variables for a basic install. You can also paste the ready-made client config above.

Does Scraper run locally?

Yes - it's a stdio server: it runs on your machine (via npx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Scraper

Alternatives to Scraper

Maintained web scraping servers if Scraper isn't the fit.

Pairs well with

Servers that cover what Scraper doesn't - only shown when the pairing reason fits the companion.

More web scraping MCP servers · Outscraper MCP Server · Web Page Fetcher · Parseur · Multi Scraper MCP · Gate402 MCP

More TypeScript MCP servers · SQLite · Microsoft 365 Admin · Clio MCP · Mycase MCP · Singapore MCP by Olano · see all