MCP Tools DirectoryAbout this integration
Web-scraping toolkit with 22 tools for structured web data as JSON for AI agents.
- Transport
- stdio
- Authentication
- api-key
- Initial setup
- credentials
- Runtime
- unattended
- Evidence
- documented
- Version
- 1.5.9
- Package
- pyscrappy
- Last compatibility test
- Not independently tested
Connect your agent
pyscrappyPublisher documentation and manifest were reviewed only. The package, websites, browser, proxies, and third-party services were not executed. Use remains subject to target-site permissions and policy; optional extras require separate installation.
Capabilities: Scrape a URL into structured text, links, images, tables, and metadata, Run site-specific research, media, commerce, and data scrapers, Render JavaScript pages with the optional browser extra, Extract site maps and use custom CSS or XPath selectors
Connected profiles
Additional details
io.github.mldsveda/pyscrappy
Source ↗ · Checked 2026-09-171.5.9
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17pypi
Source ↗ · Checked 2026-09-17pyscrappy
Source ↗ · Checked 2026-09-191.6.3
Source ↗ · Checked 2026-09-19The publisher documents a long-running MCP server with bounded response caches, retry backoff, per-domain rate limiting, and optional browser and proxy backends.
Source ↗ · Checked 2026-09-19Most documented scrapers have no credential step; the lookup_movie tool optionally uses OMDB_API_KEY, and configured third-party scraping services may use an API key.
Source ↗ · Checked 2026-09-19Install the mcp extra and run pyscrappy-mcp, which uses stdio by default; the existing catalog connection remains stdio with no endpoint.
Source ↗ · Checked 2026-09-19Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-19