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.
npx mcp-server-scraperWorks with Claude Desktop, Cursor, VS Code Copilot, and any MCP client. No accounts or API keys needed.
Demo built with remotion-readme-kit
When you're working with an AI assistant and need to reference a docs page, a blog post, or an API reference, you usually end up copy-pasting content manually. Tools like Firecrawl solve this but require a paid API key. This server does the same thing for free. It fetches a URL, runs it through Mozilla Readability (the same engine behind Firefox Reader View), and returns clean markdown. It works well for server-rendered content like documentation sites, blog posts, and articles. It won't handle JavaScript-heavy SPAs, but for the most common use case of "read this docs page and summarize it," it does the job.
Related MCP server: @hauntapi/mcp-server
Tool | What it does |
| Extract clean text content from a URL (Readability-powered) |
| Get all links with href and anchor text |
| Get title, description, OG tags, canonical, favicon |
| Search for a query string within the page, return matching lines |
| Batch scrape multiple URLs, get title + excerpt per URL |
Add to .cursor/mcp.json:
{
"mcpServers": {
"scraper": {
"command": "npx",
"args": ["-y", "mcp-server-scraper"]
}
}
}Add to claude_desktop_config.json:
{
"mcpServers": {
"scraper": {
"command": "npx",
"args": ["-y", "mcp-server-scraper"]
}
}
}Add to your MCP settings (e.g. .vscode/mcp.json):
{
"mcp": {
"servers": {
"scraper": {
"command": "npx",
"args": ["-y", "mcp-server-scraper"]
}
}
}
}"Scrape the API docs from https://docs.example.com and summarize them"
"Extract all links from this page"
"What's the OG image and description for this URL?"
"Search this page for mentions of 'authentication'"
"Scrape these 5 URLs and give me a summary of each"
Uses Mozilla Readability (the engine behind Firefox Reader View) plus linkedom for fast HTML parsing in Node. No headless browser needed. Works best with server-rendered pages: docs, blogs, articles, news sites.
This repo is an Agent Plugins 1.0.0 package: plugin.json, portable mcp.json, and skills/ ship together with the MCP server.
For Cursor, clone the repo and copy or symlink it to ~/.cursor/plugins/local/mcp-server-scraper, then reload the window. Skills and MCP show up under Customize > Plugins.
The Cursor and VS Code install buttons above still work: they add the same npx -y mcp-server-scraper stdio server as manual JSON.
A free MCP server that turns public web pages into clean markdown using Mozilla Readability. No Firecrawl or other scrape API key.
No. It fetches HTML and parses it in Node. Use a browser MCP for React dashboards and other client-rendered sites.
Firecrawl is a hosted scrape API with billing. This server runs locally via npx, costs nothing, and fits doc/blog/article URLs.
Yes. Use the local plugin path under ~/.cursor/plugins/local/mcp-server-scraper so the bundled web-scraping skill loads with the MCP config.
No. Point your MCP client at npx -y mcp-server-scraper only.
npm install
npm run typecheck
npm run build
npm testMore MCP servers and developer tools on my portfolio.
README built with README Builder
Extract all links from a page with their href and anchor text. Resolves relative URLs. Skips anchors and javascript: links.
Inputs: url (required).
Extract page metadata: title, description, Open Graph tags (og:title, og:description, og:image), canonical URL, and favicon.
Inputs: url (required).
Batch scrape multiple URLs. Returns title and excerpt for each. Failures are reported per URL without failing the whole batch.
Inputs: urls (required).
Extract clean, readable text content from a URL using Mozilla Readability. Returns title, excerpt, and main content. Best for articles, docs, and blog posts.
Inputs: url (required).
Search for a query string within the page text. Returns matching lines (one per line). Use for finding mentions of a term.
Inputs: url (required), query (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 5 tools
Each tool has a clearly distinct purpose with no overlap: extract_links focuses on hyperlinks, extract_metadata on page metadata, scrape_multiple on batch title/excerpt extraction, scrape_url on full content extraction, and search_page on text search. The descriptions make it easy to differentiate them, preventing misselection.
All tool names follow a consistent verb_noun pattern with snake_case (e.g., extract_links, scrape_url, search_page). The naming is predictable and readable throughout, with no deviations in style or convention.
With 5 tools, this server is well-scoped for web scraping purposes. Each tool earns its place by covering distinct aspects of scraping (links, metadata, batch processing, content extraction, and search), avoiding bloat while providing comprehensive functionality.
The tool set covers core web scraping workflows effectively, including extraction, metadata, batch operations, and search. A minor gap exists in lacking explicit update or delete operations, but these are not typical for scraping tasks, and agents can work around this with the provided tools.
Web scraping MCP server: any URL to Markdown or JSON, with JavaScript rendering and batch jobs.
Web scraping MCP server — scrape, extract structured data, screenshot any site with anti-bot bypass.
One MCP server for all web data. Scrape, search, crawl, and AI research in one install.
Firecrawl MCP — wraps the Firecrawl API (firecrawl.dev) for web scraping / crawling / search…