MCP Tools DirectoryAbout this integration
Web scraping MCP — extract clean markdown, links, and metadata from any URL.
- Transport
- stdio
- Authentication
- none
- Initial setup
- none
- Runtime
- unattended
- Evidence
- documented
- Version
- 1.0.1
- Package
- mcp-server-scraper
- Last compatibility test
- Not independently tested
Connect your agent
mcp-server-scraperPublisher README and npm manifest were reviewed; the package was not executed and no URL was fetched. The publisher explicitly excludes JavaScript-heavy SPA rendering and documents no account or API-key requirement. Existing identity and stdio connection are retained.
Capabilities: Extracts readable Markdown and metadata from server-rendered web pages, Extracts links and searches text within fetched pages, Batch-scrapes multiple URLs
Connected profiles
Additional details
io.github.ofershap/scraper
Source ↗ · Checked 2026-09-171.0.1
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17npm
Source ↗ · Checked 2026-09-17mcp-server-scraper
Source ↗ · Checked 2026-09-191.0.1
Source ↗ · Checked 2026-09-19Node.js executable runs locally over stdio and parses fetched HTML without a headless browser.
Source ↗ · Checked 2026-09-19No account, API key, or environment variable is documented as required.
Source ↗ · Checked 2026-09-19Existing stdio listing launches npx -y mcp-server-scraper.
Source ↗ · Checked 2026-09-19Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-19