One MCP server for all web data. Scrape, search, crawl, and AI research in one install.
This repository also configures its own agents. See what Novada-mcp tells them →
Skill Claude CodeCodex
Use Novada MCP tools for web tasks. Covers tool selection (search vs extract vs crawl vs map vs research), key parameters, common workflows, and when NOT to call each tool. Trigger: any task requiring web data, content extraction, site crawling, or multi-source research.
Skill Claude CodeCodex
When to use: Interactive flows requiring clicks, form fills, login, or chaining multiple page interactions.
Skill Claude CodeCodex
When to use: You have a URL and need its content. This is the primary content extraction tool.
Skill Claude CodeCodex
Choose the right Novada proxy type, format, and targeting options. Covers the 6 proxy types (residential/isp/mobile/datacenter/static/dedicated), when each applies, critical constraints per type, the escalation ladder, and when NOT to use proxy tools at all. Trigger: any task requiring geo-targeted HTTP requests, IP…
Skill Claude CodeCodex
When to use: You need structured records from a known platform (Amazon, TikTok, LinkedIn, GitHub, etc.) — not raw HTML, but clean tabular data. 16 platforms are in the catalog: Amazon, Walmart, SHEIN, Google (incl. Shopping), Bing, DuckDuckGo, Yandex, X/Twitter, TikTok, Instagram, Facebook, YouTube, LinkedIn, GitHub…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: