{"type":"mcp_server","name":"mcp","description":"The Hyperbrowser MCP Server provides tools for web scraping, data extraction, and crawling, offering access to browser agents like OpenAI's CUA and Anthropic's Claude Computer Use. It supports the Model Context Protocol.","category":"AI","language":"TypeScript","stars":769,"forks":6,"owner":"hyperbrowserai","github_url":"https://github.com/hyperbrowserai/mcp","homepage":null,"setup":"## Setup\n\n### Manual Installation\nTo install the server, run:\n\n```bash\nnpx hyperbrowser-mcp <YOUR-HYPERBROWSER-API-KEY>\n```\n\n## Running on Cursor\nAdd to `~/.cursor/mcp.json` like this:\n```json\n{\n  \"mcpServers\": {\n    \"hyperbrowser\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"hyperbrowser-mcp\"],\n      \"env\": {\n        \"HYPERBROWSER_API_KEY\": \"YOUR-API-KEY\"\n      }\n    }\n  }\n}\n```\n\n## Running on Windsurf\nAdd to your `./codeium/windsurf/model_config.json` like this:\n```json\n{\n  \"mcpServers\": {\n    \"hyperbrowser\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"hyperbrowser-mcp\"],\n      \"env\": {\n        \"HYPERBROWSER_API_KEY\": \"YOUR-API-KEY\"\n      }\n    }\n  }\n}\n```\n\n### Development\n\nFor development purposes, you can run the server directly from the source code.\n\n1. Clone the repository:\n\n   ```sh\n   git clone git@github.com:hyperbrowserai/mcp.git hyperbrowser-mcp\n   cd hyperbrowser-mcp\n   ```\n\n2. Install dependencies:\n\n   ```sh\n   npm install # or yarn install\n   npm run build\n   ```\n\n3. Run the server:\n\n   ```sh\n   node dist/server.js\n   ```\n\n## Claude Desktop app\nThis is an example config for the Hyperbrowser MCP server for the Claude Desktop client.\n\n```json\n{\n  \"mcpServers\": {\n    \"hyperbrowser\": {\n      \"command\": \"npx\",\n      \"args\": [\"--yes\", \"hyperbrowser-mcp\"],\n      \"env\": {\n        \"HYPERBROWSER_API_KEY\": \"your-api-key\"\n      }\n    }\n  }\n}\n```\n\n\n### Installing via Smithery\n\nTo install Hyperbrowser MCP Server for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@hyperbrowserai/mcp):\n\n```bash\nnpx -y @smithery/cli install @hyperbrowserai/mcp --client claude\n```","tools":"## Available Tools\n\n1.  `scrape_webpage` - Extract formatted (markdown, screenshot etc) content from any webpage\n2.  `crawl_webpages` - Navigate through multiple linked pages and extract LLM-friendly formatted content\n3.  `extract_structured_data` - Convert messy HTML into structured JSON\n4.  `search_with_bing` - Query the web and get results with Bing search\n5.  `browser_use_agent` - Fast, lightweight browser automation with the Browser Use agent\n6.  `openai_computer_use_agent` - General-purpose automation using OpenAI’s CUA model\n7.  `claude_computer_use_agent` - Complex browser tasks using Claude computer use","faq":null,"created_at":"2025-02-25T19:06:01+00:00","updated_at":"2025-03-28T23:59:36+00:00","source_url":"https://model-context-protocol.com/servers/hyperbrowser-mcp-server-web-scraping","related_articles":[]}