extract
URL -> smart chunks dict (cleantext + markdown + structureddata + codeblocks + metadata) via web-core 5-strategy chain. Batch processing (up to 50 URLs), deep crawling, site mapping, local file conversion (PDF/DOCX/XLSX/PPTX/EPUB), structured extraction (JSON Schema)
How to use it
extract is exposed by the Wet MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the extract tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Wet MCP
claude mcp add wet -- uvx wet-mcpOther tools in Wet MCP (4)
Re-trigger the zero-config relay setup flow (prints a fresh relay URL for the browser form). Registered via mcp-core's registeropenrelaytool so an LLM can restart setup without a manual restart.
Per-tool documentation: search, extract, media, config
list (discover URLs from gallery pages), download (SSRF-safe). analyze was removed in v2.0.0 -- use imagine-mcp.understand instead
Web (SearXNG metasearch), news, images, academic research (Scholar / arXiv / PubMed / CrossRef / Semantic Scholar / BASE), library docs (HyDE + FTS5), find similar pages. Includes docsresolve (library name -> ranked id), docsquery (version-aware + topic + 5000-token cap), docslockproject (Cabinets p