Server facts
watercrawl-mcp
Project
- Author
- watercrawl
- Repository
- github.com/watercrawl/watercrawl-mcp
- License
- Not specified
- Category
- Search & Web Data
Tech
- Runtime / language
- node
- Transports
- stdio
- Remote available
- No
- Authentication
- Not specified
Activity
- GitHub stars
- 8
- Last commit
- Data as of
Tags
- Web Crawling
- mcp
- watercrawl
Overview
Web content retrieval and request tracking sit together in WaterCrawl MCP, which connects AI assistants to WaterCrawl through a FastMCP-based interface. Its scrape-url tool accepts page-level controls for tag selection, main-content extraction, links, HTML, locale, headers, and cookie acceptance. Page actions can request screenshots or PDFs. The search tool supports language and country settings, time ranges, search type, depth, and result limits, letting an assistant configure retrieval rather than submit only a query. Scraping and search requests also expose synchronous execution and download options.
The remaining tools handle work after a request has been submitted. manage-crawl can inspect or list crawl requests, stop them, and retrieve their results; manage-search provides listing, inspection, and stopping for searches. monitor-request follows either request type in real time with a configurable timeout. For crawl output, download-sitemap offers JSON, graph, or Markdown formats. Setup requires a WaterCrawl API key and supports environment variables or command-line configuration. The documentation includes Codeium/Windsurf configuration and an SSE connection workflow for Claude Desktop.
watercrawl-mcp setup notes
- watercrawl-mcp records stdio only; confirm a network transport upstream before planning remote access.
- watercrawl-mcp has no recorded license; confirm reuse terms in its repository.