{"skill":{"slug":"openclaw-web-search-mcp","displayName":"Openclaw Web Search Mcp","summary":"Provides AI agents with web search, page and PDF extraction, YouTube transcripts, summarization, semantic search, and automated research workflows.","description":"# Web Search and Research MCP\n\nThis MCP provides comprehensive web browsing, search, and research capabilities for AI agents, including PDF extraction, YouTube transcripts, summarization, and semantic search.\n\n## Overview\n\nThis MCP implements a full suite of tools for AI agents to interact with the web:\n- Google search integration\n- Web page content extraction\n- Link extraction from pages\n- PDF text extraction\n- YouTube video transcript retrieval\n- Text summarization\n- Text embedding and semantic search\n- Automated research workflows\n\n## Features\n\n- **Search**: Perform Google searches and get structured results\n- **Page Extraction**: Extract clean text content from web pages\n- **Link Extraction**: Get all links from a webpage\n- **PDF Processing**: Extract text from PDF documents\n- **YouTube Transcripts**: Retrieve transcripts from YouTube videos\n- **Summarization**: Generate concise summaries of text content\n- **Embeddings**: Store and search text using semantic embeddings\n- **Research**: Automated multi-step research workflows\n\n## Tools\n\n- `search` - Google search with results\n- `open_page` - Extract text from web pages\n- `extract_links` - Get links from pages\n- `extract_pdf` - Extract text from PDFs\n- `youtube_transcript` - Get YouTube video transcripts\n- `summarize` - Summarize text content\n- `embed` - Store text embeddings\n- `semantic_search` - Search stored embeddings\n- `research` - Conduct automated research\n\n## Installation\n\n```bash\nnpm install\n```\n\n## Usage\n\nRun the MCP server:\n```bash\nnode index.js <tool_name> <json_input>\n```\n\nExample:\n```bash\nnode index.js search '{\"query\":\"artificial intelligence\"}'\n```\n\n## Dependencies\n\n- axios: HTTP requests\n- cheerio: HTML parsing\n- natural: Text processing\n- pdf-parse: PDF text extraction\n- youtube-transcript: YouTube transcript API","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":765,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1772886187996,"updatedAt":1779077782515},"latestVersion":{"version":"1.0.0","createdAt":1772886187996,"changelog":"Initial release providing comprehensive web search and research tools for AI agents:\n\n- Google search with structured results\n- Web page and PDF text extraction\n- YouTube video transcript retrieval\n- Summarization and semantic search capabilities\n- Automated multi-step research workflows","license":null},"metadata":null,"owner":{"handle":"nishant-clawit","userId":"s17csax3ye8qpp891dpychxc11885f18","displayName":"nishant-clawit","image":"https://avatars.githubusercontent.com/u/261710652?v=4"},"moderation":{"isSuspicious":false,"isMalwareBlocked":false,"verdict":"clean","reasonCodes":["review.llm_review"],"summary":"Review: review.llm_review","engineVersion":"v2.4.24","updatedAt":1780089793935}}