DeveloperWebMCP verified
Krawl is a deep research agent API that produces 50+ source reports in 90 seconds with full citations, searching the web, X/Twitter, GitHub, academic papers, and crypto/DeFi in parallel. Drop it into Claude Code, OpenClaw, Hermes, or any runtime via API, MCP, or skill.md.
Krawl is a deep research agent API that produces 50+ source reports in 90 seconds with full citations, searching the web, X/Twitter, GitHub, academic papers, and crypto/DeFi in parallel. Drop it into Claude Code, OpenClaw, Hermes, or any runtime via API, MCP, or skill.md. This page documents every listed tool, the action or answer it provides, its installation command, and the input fields an agent should send.
Run an autonomous deep-research agent over a topic and return a comprehensive markdown report with 50+ verified sources and inline citations. Searches the web, X/Twitter, GitHub, academic papers, and crypto/DeFi data in parallel, then synthesizes a cited answer.
Open the krawl.sh website and ask your browser agent to use researchInstall browse first, then run the command in a terminal. WebMCP tools run directly on the website and do not need a package install.
Use the research tool on krawl.sh with query: <string>, mode: <string>. Return the structured result and cite the source page.query string The research question or topic to investigate.mode string deep = exhaustive multi-source search; quick = fast shallow answer; crypto = on-chain/DeFi-specialized research.Search a single source and return raw, structured results without synthesis. Faster and cheaper than `research`; use when you want links/snippets from one provider rather than a written report.
Open the krawl.sh website and ask your browser agent to use quick_searchInstall browse first, then run the command in a terminal. WebMCP tools run directly on the website and do not need a package install.
Use the quick_search tool on krawl.sh with query: <string>, source: <string>, num_results: <integer>. Return the structured result and cite the source page.query string The search query.source string Which source to search (exa=general web, x=Twitter, etc.).num_results integer Max results to return.Ask a natural-language question about Krawl's research capabilities and get a routed answer pointing to the right tool or endpoint.
Open the krawl.sh website and ask your browser agent to use ask_krawlInstall browse first, then run the command in a terminal. WebMCP tools run directly on the website and do not need a package install.
Use the ask_krawl tool on krawl.sh with query: <string>. Return the structured result and cite the source page.query string A natural-language question about what you want to research or how to use Krawl.