{"type":"mcp_server","name":"mcp-webresearch","description":"This repository provides an MCP server for web research, integrating Google search, webpage content extraction, research session tracking, and screenshot capture for use with the Claude Desktop app.","category":"Search & Knowledge","language":"JavaScript","stars":300,"forks":37,"owner":"mzxrai","github_url":"https://github.com/mzxrai/mcp-webresearch","homepage":null,"setup":"## Setup\n\n1.  Ensure you've downloaded and installed the [Claude Desktop app](https://claude.ai/download) and you have npm installed.\n2.  Add the following entry to your `claude_desktop_config.json` (on Mac, found at `~/Library/Application\\ Support/Claude/claude_desktop_config.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"webresearch\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@mzxrai/mcp-webresearch@latest\"]\n    }\n  }\n}\n```\nThis config allows Claude Desktop to automatically start the web research MCP server when needed.","tools":"## Available Tools\n\n1.  Google search integration (Performs Google searches and extracts results)\n2.  Webpage content extraction (Visits a webpage and extracts its content)\n3.  Research session tracking (Tracks list of visited pages, search queries, etc.)\n4.  Screenshot capture (Takes a screenshot of the current page)\n5.  `search_google` (Performs Google searches and extracts results with `{ query: string }` argument)\n6.  `visit_page` (Visits a webpage and extracts its content with `{ url: string, takeScreenshot?: boolean }` argument)\n7.  `take_screenshot` (Takes a screenshot of the current page with no arguments required)","faq":null,"created_at":"2024-12-06T04:28:52+00:00","updated_at":"2025-03-27T07:07:24+00:00","source_url":"https://model-context-protocol.com/servers/mcp-web-research-server-claude-integration","related_articles":[]}