{
  "markdown": "# Crawleo MCP Server\n\n<a href=\"https://glama.ai/mcp/servers/@crawleo/crawleo-mcp\">\n  <img width=\"380\" height=\"200\" src=\"https://glama.ai/mcp/servers/@crawleo/crawleo-mcp/badge\" alt=\"Crawleo MCP server\" />\n</a>\n\n\n[![smithery badge](https://smithery.ai/badge/crawleo/crawleo)](https://smithery.ai/server/crawleo/crawleo)\n\nReal-time web search and crawling capabilities for AI assistants through Model Context Protocol (MCP).\n\n## Overview\n\nCrawleo MCP enables AI assistants to access live web data through two powerful tools:\n- **web.search** - Real-time web search with multiple output formats\n- **web.crawl** - Deep content extraction from any URL\n\n## Features\n\n✅ **Real-time web search** from any country/language  \n✅ **Multiple output formats** - Enhanced HTML, Raw HTML, Markdown, Plain Text  \n✅ **Device-specific results** - Desktop, mobile, or tablet view  \n✅ **Deep content extraction** with JavaScript rendering  \n✅ **Zero data retention** - Complete privacy  \n✅ **Auto-crawling** option for search results  \n\n---\n\n## Installation\n\n### Option 1: NPM (Recommended for local usage)\n\nInstall globally via npm:\n\n```bash\nnpm install -g crawleo-mcp\n```\n\nOr use npx without installing:\n\n```bash\nnpx crawleo-mcp\n```\n\n### Option 2: Clone Repository\n\n```bash\ngit clone https://github.com/Crawleo/Crawleo-MCP.git\ncd Crawleo-MCP\nnpm install\nnpm run build\n```\n\n### Option 3: Docker\n\nBuild and run using Docker:\n\n```bash\n# Build the image\ndocker build -t crawleo-mcp .\n\n# Run with your API key\ndocker run -e CRAWLEO_API_KEY=your_api_key crawleo-mcp\n```\n\n**Docker configuration for MCP clients:**\n\n```json\n{\n  \"mcpServers\": {\n    \"crawleo\": {\n      \"command\": \"docker\",\n      \"args\": [\"run\", \"-i\", \"--rm\", \"-e\", \"CRAWLEO_API_KEY=YOUR_API_KEY_HERE\", \"crawleo-mcp\"]\n    }\n  }\n}\n```\n\n### Option 4: Remote Server (No installation needed)\n\nUse the hosted version at `https://api.crawleo.dev/mcp` - see configuration examples below.\n\n---\n\n## Getting Your API Key\n\n1. Visit [crawleo.dev](https://crawleo.dev)\n2. Sign up for a free account\n3. Navigate to your dashboard\n4. Copy your API key (starts with `sk_`)\n\n---\n\n## Setup Instructions\n\n### Using Local MCP Server (npm package)\n\nAfter installing via npm, configure your MCP client to use the local server:\n\n**Claude Desktop / Cursor / Windsurf (Local):**\n\n```json\n{\n  \"mcpServers\": {\n    \"crawleo\": {\n      \"command\": \"npx\",\n      \"args\": [\"crawleo-mcp\"],\n      \"env\": {\n        \"CRAWLEO_API_KEY\": \"YOUR_API_KEY_HERE\"\n      }\n    }\n  }\n}\n```\n\n**Or if installed globally:**\n\n```json\n{\n  \"mcpServers\": {\n    \"crawleo\": {\n      \"command\": \"crawleo-mcp\",\n      \"env\": {\n        \"CRAWLEO_API_KEY\": \"YOUR_API_KEY_HERE\"\n      }\n    }\n  }\n}\n```\n\n**From cloned repository:**\n\n```json\n{\n  \"mcpServers\": {\n    \"crawleo\": {\n      \"command\": \"node\",\n      \"args\": [\"/path/to/Crawleo-MCP/dist/index.js\"],\n      \"env\": {\n        \"CRAWLEO_API_KEY\": \"YOUR_API_KEY_HERE\"\n      }\n    }\n  }\n}\n```\n\n---\n\n### Using Remote Server (Hosted)\n\n#### 1. Claude Desktop\n\n**Location of config file:**\n\n- **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`\n- **Windows**: `%APPDATA%\\Claude\\claude_desktop_config.json`\n- **Linux**: `~/.config/Claude/claude_desktop_config.json`\n\n**Configuration:**\n\n```json\n{\n  \"mcpServers\": {\n    \"crawleo\": {\n      \"url\": \"https://api.crawleo.dev/mcp\",\n      \"transport\": \"http\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY_HERE\"\n      }\n    }\n  }\n}\n```\n\nReplace `YOUR_API_KEY_HERE` with your actual API key from crawleo.dev.\n\n**Steps:**\n1. Open the config file in a text editor\n2. Add the Crawleo MCP configuration\n3. Save the file\n4. Restart Claude Desktop completely (quit and reopen)\n5. Start a new conversation and ask Claude to search the web!\n\n**Example usage:**\n```\n\"Search for the latest AI news and summarize the top 5 articles\"\n\"Find Python web scraping tutorials and extract code examples\"\n```\n\n---\n\n### 2. Cursor IDE\n\n**Location of config file:**\n\n- **macOS**: `~/.cursor/config.json` or `~/Library/Application Support/Cursor/config.json`\n- **Windows**: `%APPDATA%\\Cursor\\config.json`\n- **Linux**: `~/.config/Cursor/config.json`\n\n**Configuration:**\n\n```json\n{\n  \"mcpServers\": {\n    \"crawleo\": {\n      \"url\": \"https://api.crawleo.dev/mcp\",\n      \"transport\": \"http\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY_HERE\"\n      }\n    }\n  }\n}\n```\n\n**Steps:**\n1. Locate and open your Cursor config file\n2. Add the Crawleo MCP configuration\n3. Save the file\n4. Restart Cursor\n5. The MCP tools will be available in your AI assistant\n\n**Example usage in Cursor:**\n```\n\"Search for React best practices and add them to my code comments\"\n\"Find the latest documentation for this API endpoint\"\n```\n\n---\n\n### 3. Windsurf IDE\n\n**Location of config file:**\n\n- **macOS**: `~/Library/Application Support/Windsurf/config.json`\n- **Windows**: `%APPDATA%\\Windsurf\\config.json`\n- **Linux**: `~/.config/Windsurf/config.json`\n\n**Configuration:**\n\n```json\n{\n  \"mcpServers\": {\n    \"crawleo\": {\n      \"url\": \"https://api.crawleo.dev/mcp\",\n      \"transport\": \"http\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY_HERE\"\n      }\n    }\n  }\n}\n```\n\n**Steps:**\n1. Open the Windsurf config file\n2. Add the Crawleo MCP server configuration\n3. Save and restart Windsurf\n4. Start using web search in your coding workflow\n\n---\n\n### 4. GitHub Copilot\n\n**Location of config file:**\n\nFor GitHub Copilot in VS Code or compatible editors, you need to configure MCP servers.\n\n**Configuration:**\n\nCreate or edit your MCP config file and add:\n\n```json\n{\n  \"servers\": {\n    \"Crawleo\": {\n      \"url\": \"https://api.crawleo.dev/mcp\",\n      \"transport\": \"http\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY_HERE\"\n      }\n    }\n  }\n}\n```\n\n**Complete example with multiple servers:**\n\n```json\n{\n  \"servers\": {\n    \"Crawleo\": {\n      \"url\": \"https://api.crawleo.dev/mcp\",\n      \"transport\": \"http\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY_HERE\"\n      }\n    }\n  }\n}\n```\n\n**Steps:**\n1. Open your GitHub Copilot MCP configuration\n2. Add the Crawleo server configuration\n3. Save the file\n4. Restart VS Code or your IDE\n5. GitHub Copilot can now use Crawleo for web searches!\n\n**Example usage:**\n```\nAsk Copilot: \"Search for the latest Python best practices\"\nAsk Copilot: \"Find documentation for this library\"\n```\n\n---\n\n### 5. OpenAI Platform (Direct Integration)\n\nOpenAI now supports MCP servers directly! Here's how to use Crawleo with OpenAI's API:\n\n**Python Example:**\n\n```python\nfrom openai import OpenAI\n\nclient = OpenAI()\n\nresponse = client.responses.create(\n    model=\"gpt-4\",\n    input=[\n        {\n            \"role\": \"user\",\n            \"content\": [\n                {\n                    \"type\": \"input_text\",\n                    \"text\": \"search for latest news about openai models\"\n                }\n            ]\n        }\n    ],\n    text={\n        \"format\": {\n            \"type\": \"text\"\n        },\n        \"verbosity\": \"medium\"\n    },\n    reasoning={\n        \"effort\": \"medium\"\n    },\n    tools=[\n        {\n            \"type\": \"mcp\",\n            \"server_label\": \"Crawleo\",\n            \"server_url\": \"https://api.crawleo.dev/mcp\",\n            \"server_description\": \"Crawleo MCP Server - Real-Time Web Knowledge for AI\",\n            \"authorization\": \"YOUR_API_KEY_HERE\",\n            \"allowed_tools\": [\n                \"web.search\",\n                \"web.crawl\"\n            ],\n            \"require_approval\": \"always\"\n        }\n    ],\n    store=True,\n    include=[\n        \"reasoning.encrypted_content\",\n        \"web_search_call.action.sources\"\n    ]\n)\n\nprint(response)\n```\n\n**Key Parameters:**\n- `server_url` - Crawleo MCP endpoint\n- `authorization` - Your Crawleo API key\n- `allowed_tools` - Enable `web.search` and/or `web.crawl`\n- `require_approval` - Set to \"always\", \"never\", or \"conditional\"\n\n**Node.js Example:**\n\n```javascript\nimport OpenAI from 'openai';\n\nconst client = new OpenAI();\n\nconst response = await client.responses.create({\n  model: 'gpt-4',\n  input: [\n    {\n      role: 'user',\n      content: [\n        {\n          type: 'input_text',\n          text: 'search for latest AI developments'\n        }\n      ]\n    }\n  ],\n  tools: [\n    {\n      type: 'mcp',\n      server_label: 'Crawleo',\n      server_url: 'https://api.crawleo.dev/mcp',\n      server_description: 'Crawleo MCP Server - Real-Time Web Knowledge for AI',\n      authorization: 'YOUR_API_KEY_HERE',\n      allowed_tools: ['web.search', 'web.crawl'],\n      require_approval: 'always'\n    }\n  ]\n});\n\nconsole.log(response);\n```\n\n---\n\n## Available Tools\n\n### web.search\n\nSearch the web in real-time with customizable parameters.\n\n**Parameters:**\n- `query` *(required)* - Search term\n- `max_pages` - Number of result pages (default: 1)\n- `setLang` - Language code (e.g., \"en\", \"ar\")\n- `cc` - Country code (e.g., \"US\", \"EG\")\n- `device` - Device type: \"desktop\", \"mobile\", \"tablet\" (default: \"desktop\")\n- `enhanced_html` - Get clean HTML (default: true)\n- `raw_html` - Get raw HTML (default: false)\n- `markdown` - Get Markdown format (default: true)\n- `page_text` - Get plain text (default: false)\n- `auto_crawling` - Auto-crawl result URLs (default: false)\n\n**Example:**\n```\nAsk your AI: \"Search for 'Python web scraping' and return results in Markdown\"\n```\n\n---\n\n### web.crawl\n\nExtract content from specific URLs.\n\n**Parameters:**\n- `urls` *(required)* - List of URLs to crawl\n- `rawHtml` - Return raw HTML (default: false)\n- `markdown` - Convert to Markdown (default: false)\n- `screenshot` - Capture screenshot (optional)\n- `country` - Geographic location\n\n**Example:**\n```\nAsk your AI: \"Crawl https://example.com and extract the main content in Markdown\"\n```\n\n---\n\n## Troubleshooting\n\n### MCP server not appearing\n\n1. **Check config file location** - Make sure you're editing the correct file\n2. **Verify JSON syntax** - Use a JSON validator to check for syntax errors\n3. **Restart the application** - Completely quit and reopen (not just reload)\n4. **Check API key** - Ensure your API key is valid and active at crawleo.dev\n\n### Authentication errors\n\n- Verify your API key is correct (should start with `sk_`)\n- Make sure the key is wrapped in quotes\n- Check that \"Bearer \" prefix is included in the Authorization header (for Claude/Cursor/Windsurf)\n- For OpenAI Platform, use the key directly in the `authorization` field\n- Confirm your account has available credits at crawleo.dev\n\n### No results returned\n\n- Check your internet connection\n- Verify the search query is not empty\n- Try a simpler search query first\n- Check API status at crawleo.dev\n\n### Tool names not recognized\n\nMake sure you're using the correct tool names:\n- Use `web.search` (not `search_web`)\n- Use `web.crawl` (not `crawl_web`)\n\n---\n\n## Usage Examples\n\n### Research Assistant\n```\n\"Search for recent developments in quantum computing and summarize the key findings\"\n```\n\n### Content Analysis\n```\n\"Search for competitor pricing pages and extract their pricing tiers\"\n```\n\n### Code Documentation\n```\n\"Find the official documentation for FastAPI and extract the quickstart guide\"\n```\n\n### News Monitoring\n```\n\"Search for today's news about artificial intelligence from US sources\"\n```\n\n### Market Research\n```\n\"Search for customer reviews of iPhone 15 and analyze sentiment\"\n```\n\n---\n\n## Pricing\n\nCrawleo MCP uses the same affordable pricing as our API:\n- **10,000 searches** → $20\n- **100,000 searches** → $100\n- **250,000 searches** → $200\n\nCheck your usage and manage your subscription at [crawleo.dev](https://crawleo.dev)\n\n---\n\n## Privacy & Security\n\n✅ **Zero data retention** - We never store your search queries or results  \n✅ **Secure authentication** - API keys transmitted over HTTPS  \n✅ **No tracking** - Your usage patterns remain private  \n\n---\n\n## Support\n\n- **Documentation**: [crawleo.dev/docs](https://crawleo.dev/docs)\n- **API Status**: [crawleo.dev/status](https://crawleo.dev/status)\n- **Contact**: support@crawleo.dev\n\n---\n\n## Links\n\n- 🌐 Website: [crawleo.dev](https://crawleo.dev)\n- 📚 Documentation: [crawleo.dev/docs](https://crawleo.dev/docs)\n- 🔑 Get API Key: [crawleo.dev](https://crawleo.dev)\n\n\n\n\n---\n\nIs this better? Would you like me to add anything else or create additional guides?\n",
  "bytes": 12190,
  "sha": "81c7613a39f6c4ef36cb2b92158fa2b37ee1cc62f7c237f324dc5f74ecd77ca2",
  "repo_slug": "crawleo/crawleo-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_crawleo_crawleo_mcp_de25b934/readme"
}