{
  "markdown": "# ScrapeGraph MCP Server\n\n<p align=\"center\">\n  <img src=\"./assets/scrapegraphAI.svg\" width=\"250\" alt=\"ScrapegraphAI Logo\">\n</p>\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![Python 3.13+](https://img.shields.io/badge/python-3.13+-blue.svg)](https://www.python.org/downloads/)\n[![smithery badge](https://smithery.ai/badge/@ScrapeGraphAI/scrapegraph-mcp)](https://smithery.ai/server/@ScrapeGraphAI/scrapegraph-mcp)\n\n\nA production-ready [Model Context Protocol](https://modelcontextprotocol.io/introduction) (MCP) server that provides seamless integration with the [ScrapeGraph AI](https://scrapegraphai.com) API. This server enables language models to leverage advanced AI-powered web scraping capabilities with enterprise-grade reliability.\n\n## Table of Contents\n\n- [Key Features](#key-features)\n- [Quick Start](#quick-start)\n- [Available Tools](#available-tools)\n- [Setup Instructions](#setup-instructions)\n- [Remote Server Usage](#remote-server-usage)\n- [Local Usage](#local-usage)\n- [Google ADK Integration](#google-adk-integration)\n- [Example Use Cases](#example-use-cases)\n- [Error Handling](#error-handling)\n- [Common Issues](#common-issues)\n- [Development](#development)\n- [Contributing](#contributing)\n- [Documentation](#documentation)\n- [Technology Stack](#technology-stack)\n- [License](#license)\n\n## API v2\n\nThis MCP server targets **ScrapeGraph API v2** (`https://v2-api.scrapegraphai.com/api`), aligned 1:1 with\n[scrapegraph-py PR #84](https://github.com/ScrapeGraphAI/scrapegraph-py/pull/84). Auth uses the\n`SGAI-APIKEY` header. Environment variables mirror the Python SDK:\n\n- **`SGAI_API_URL`** — override the base URL (default `https://v2-api.scrapegraphai.com/api`)\n- **`SGAI_TIMEOUT`** — request timeout in seconds (default `120`)\n- **`SGAI_API_KEY`** — API key (can also be passed via MCP `scrapegraphApiKey` or `X-API-Key` header)\n\n> Legacy aliases (still honored): `SCRAPEGRAPH_API_BASE_URL` for `SGAI_API_URL`, `SGAI_TIMEOUT_S` for `SGAI_TIMEOUT`.\n\n## Key Features\n\n- **Scrape & extract**: `scrape` (POST /scrape, multi-format), `extract` (POST /extract, URL + prompt)\n- **Search**: `search` (POST /search; `num_results` clamped 3–20)\n- **Crawl**: Async multi-page crawl with `crawl_start` / `crawl_get_status` / `crawl_stop` / `crawl_resume`\n- **Schema**: `schema` (POST /schema) — generate or augment a JSON Schema from a prompt\n- **Monitors**: Scheduled jobs via `monitor_create`, `monitor_list`, `monitor_get`, pause/resume/delete, `monitor_activity` (paginated tick history)\n- **Account**: `credits`, `history`\n- **Easy integration**: Claude Desktop, Cursor, Smithery, HTTP transport\n- **Developer docs**: `.agent/` folder\n\n## Migration: v2 → v3\n\nv3 renames every MCP tool that diverged from the v2 API docs. **Hard rename, no aliases.**\n\n| v2 (old) | v3 (new) |\n|---|---|\n| `smartscraper` | `extract` |\n| `searchscraper` | `search` |\n| `smartcrawler_initiate` | `crawl_start` |\n| `smartcrawler_fetch_results` | `crawl_get_status` |\n| `sgai_history` | `history` |\n| `generate_schema` | `schema` |\n| `markdownify` | **removed** — use `scrape` with `output_format=\"markdown\"` |\n\n## Quick Start\n\n### 1. Get Your API Key\n\nSign up and get your API key from the [ScrapeGraph Dashboard](https://dashboard.scrapegraphai.com)\n\n### 2. Install with Smithery (Recommended)\n\n```bash\nnpx -y @smithery/cli install @ScrapeGraphAI/scrapegraph-mcp --client claude\n```\n\n### 3. Start Using\n\nAsk Claude or Cursor:\n- \"Convert https://scrapegraphai.com to markdown\"\n- \"Extract all product prices from this e-commerce page\"\n- \"Research the latest AI developments and summarize findings\"\n\nThat's it! The server is now available to your AI assistant.\n\n## Available Tools\n\n| Tool | Role |\n|------|------|\n| `scrape` | POST /scrape (`output_format`: markdown, html, screenshot, branding, links, images, summary) |\n| `extract` | POST /extract (requires `website_url` + `user_prompt`; optional `output_schema`) |\n| `search` | POST /search (`num_results` 1–20; supports `country_search`, `time_range`, `output_schema`) |\n| `crawl_start` | POST /crawl — `extraction_mode` markdown / html / links / images / summary / branding / screenshot |\n| `crawl_get_status` | GET /crawl/:id (poll until `status: completed`) |\n| `crawl_stop`, `crawl_resume` | POST /crawl/:id/stop \\| resume |\n| `schema` | POST /schema (generate or augment a JSON Schema from a prompt) |\n| `credits` | GET /credits |\n| `history` | GET /history (paginated, `service` filter) |\n| `monitor_create`, `monitor_list`, `monitor_get`, `monitor_pause`, `monitor_resume`, `monitor_delete` | /monitor API |\n| `monitor_activity` | GET /monitor/:id/activity (paginated tick history: `id`, `createdAt`, `status`, `changed`, `elapsedMs`, `diffs`) |\n\n**Removed:** `sitemap`, `agentic_scrapper`, async-status polling, and (in v3) `markdownify` — use `scrape` with `output_format=\"markdown\"`.\n\n## Setup Instructions\n\nTo utilize this server, you'll need a ScrapeGraph API key. Follow these steps to obtain one:\n\n1. Navigate to the [ScrapeGraph Dashboard](https://dashboard.scrapegraphai.com)\n2. Create an account and generate your API key\n\n### Automated Installation via Smithery\n\nFor automated installation of the ScrapeGraph API Integration Server using [Smithery](https://smithery.ai/server/@ScrapeGraphAI/scrapegraph-mcp):\n\n```bash\nnpx -y @smithery/cli install @ScrapeGraphAI/scrapegraph-mcp --client claude\n```\n\n### Claude Desktop Configuration\n\nUpdate your Claude Desktop configuration file with the following settings (located on the top rigth of the Cursor page):\n\n(remember to add your API key inside the config)\n\n```json\n{\n    \"mcpServers\": {\n        \"@ScrapeGraphAI-scrapegraph-mcp\": {\n            \"command\": \"npx\",\n            \"args\": [\n                \"-y\",\n                \"@smithery/cli@latest\",\n                \"run\",\n                \"@ScrapeGraphAI/scrapegraph-mcp\",\n                \"--config\",\n                \"\\\"{\\\\\\\"scrapegraphApiKey\\\\\\\":\\\\\\\"YOUR-SGAI-API-KEY\\\\\\\"}\\\"\"\n            ]\n        }\n    }\n}\n```\n\nThe configuration file is located at:\n- Windows: `%APPDATA%/Claude/claude_desktop_config.json`\n- macOS: `~/Library/Application\\ Support/Claude/claude_desktop_config.json`\n\n### Cursor Integration\n\nAdd the ScrapeGraphAI MCP server on the settings:\n\n![Cursor MCP Integration](assets/cursor_mcp.png)\n\n## Remote Server Usage\n\nConnect to our hosted MCP server - no local installation required!\n\n> [!WARNING]\n> The legacy MCP endpoint at `https://mcp.scrapegraphai.com/mcp` will be\n> deprecated soon. New integrations should use the replacement MCP endpoint:\n> `https://sgai-mcp-main.onrender.com`.\n\n### Claude Desktop Configuration (Remote)\n\nAdd this to your Claude Desktop config (`~/Library/Application Support/Claude/claude_desktop_config.json` on macOS):\n\n```json\n{\n  \"mcpServers\": {\n    \"scrapegraph-mcp\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"mcp-remote@0.1.25\",\n        \"https://sgai-mcp-main.onrender.com\",\n        \"--header\",\n        \"X-API-Key:YOUR_API_KEY\"\n      ]\n    }\n  }\n}\n```\n\n### Cursor Configuration (Remote)\n\nCursor supports native HTTP MCP connections. Add to your Cursor MCP settings (`~/.cursor/mcp.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"scrapegraph-mcp\": {\n      \"url\": \"https://sgai-mcp-main.onrender.com\",\n      \"headers\": {\n        \"X-API-Key\": \"YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\n### Benefits of Remote Server\n\n- **No local setup** - Just configure and start using\n- **Always up-to-date** - Automatically receives latest updates\n- **Cross-platform** - Works on any OS with Node.js\n\n## Local Usage\n\nTo run the MCP server locally for development or testing, follow these steps:\n\n### Prerequisites\n\n- Python 3.13 or higher\n- pip or uv package manager\n- ScrapeGraph API key\n\n### Installation\n\n1. **Clone the repository** (if you haven't already):\n\n```bash\ngit clone https://github.com/ScrapeGraphAI/scrapegraph-mcp\ncd scrapegraph-mcp\n```\n\n2. **Install the package**:\n\n```bash\n# Using pip\npip install -e .\n\n# Or using uv (faster)\nuv pip install -e .\n```\n\n3. **Set your API key**:\n\n```bash\n# macOS/Linux\nexport SGAI_API_KEY=your-api-key-here\n\n# Windows (PowerShell)\n$env:SGAI_API_KEY=\"your-api-key-here\"\n\n# Windows (CMD)\nset SGAI_API_KEY=your-api-key-here\n```\n\n### Running the Server Locally\n\nYou can run the server directly:\n\n```bash\n# Using the installed command\nscrapegraph-mcp\n\n# Or using Python module\npython -m scrapegraph_mcp.server\n```\n\nThe server will start and communicate via stdio (standard input/output), which is the standard MCP transport method.\n\n### Testing with MCP Inspector\n\nTest your local server using the MCP Inspector tool:\n\n```bash\nnpx @modelcontextprotocol/inspector python -m scrapegraph_mcp.server\n```\n\nThis provides a web interface to test all available tools interactively.\n\n### Configuring Claude Desktop for Local Server\n\nTo use your locally running server with Claude Desktop, update your configuration file:\n\n**macOS/Linux** (`~/Library/Application Support/Claude/claude_desktop_config.json`):\n\n```json\n{\n    \"mcpServers\": {\n        \"scrapegraph-mcp-local\": {\n            \"command\": \"python\",\n            \"args\": [\n                \"-m\",\n                \"scrapegraph_mcp.server\"\n            ],\n            \"env\": {\n                \"SGAI_API_KEY\": \"your-api-key-here\"\n            }\n        }\n    }\n}\n```\n\n**Windows** (`%APPDATA%\\Claude\\claude_desktop_config.json`):\n\n```json\n{\n    \"mcpServers\": {\n        \"scrapegraph-mcp-local\": {\n            \"command\": \"python\",\n            \"args\": [\n                \"-m\",\n                \"scrapegraph_mcp.server\"\n            ],\n            \"env\": {\n                \"SGAI_API_KEY\": \"your-api-key-here\"\n            }\n        }\n    }\n}\n```\n\n**Note**: Make sure Python is in your PATH. You can verify by running `python --version` in your terminal.\n\n### Configuring Cursor for Local Server\n\nIn Cursor's MCP settings, add a new server with:\n\n- **Command**: `python`\n- **Args**: `[\"-m\", \"scrapegraph_mcp.server\"]`\n- **Environment Variables**: `{\"SGAI_API_KEY\": \"your-api-key-here\"}`\n\n### Troubleshooting Local Setup\n\n**Server not starting:**\n- Verify Python is installed: `python --version`\n- Check that the package is installed: `pip list | grep scrapegraph-mcp`\n- Ensure API key is set: `echo $SGAI_API_KEY` (macOS/Linux) or `echo %SGAI_API_KEY%` (Windows)\n\n**Tools not appearing:**\n- Check Claude Desktop logs:\n  - macOS: `~/Library/Logs/Claude/`\n  - Windows: `%APPDATA%\\Claude\\Logs\\`\n- Verify the server starts without errors when run directly\n- Check that the configuration JSON is valid\n\n**Import errors:**\n- Reinstall the package: `pip install -e . --force-reinstall`\n- Verify dependencies: `pip install -r requirements.txt` (if available)\n\n## Google ADK Integration\n\nThe ScrapeGraph MCP server can be integrated with [Google ADK (Agent Development Kit)](https://github.com/google/adk) to create AI agents with web scraping capabilities.\n\n### Prerequisites\n\n- Python 3.13 or higher\n- Google ADK installed\n- ScrapeGraph API key\n\n### Installation\n\n1. **Install Google ADK** (if not already installed):\n\n```bash\npip install google-adk\n```\n\n2. **Set your API key**:\n\n```bash\nexport SGAI_API_KEY=your-api-key-here\n```\n\n### Basic Integration Example\n\nCreate an agent file (e.g., `agent.py`) with the following configuration:\n\n```python\nimport os\nfrom google.adk.agents import LlmAgent\nfrom google.adk.tools.mcp_tool.mcp_toolset import MCPToolset\nfrom google.adk.tools.mcp_tool.mcp_session_manager import StdioConnectionParams\nfrom mcp import StdioServerParameters\n\n# Path to the scrapegraph-mcp server directory\nSCRAPEGRAPH_MCP_PATH = \"/path/to/scrapegraph-mcp\"\n\n# Path to the server.py file\nSERVER_SCRIPT_PATH = os.path.join(\n    SCRAPEGRAPH_MCP_PATH, \n    \"src\", \n    \"scrapegraph_mcp\", \n    \"server.py\"\n)\n\nroot_agent = LlmAgent(\n    model='gemini-2.0-flash',\n    name='scrapegraph_assistant_agent',\n    instruction='Help the user with web scraping and data extraction using ScrapeGraph AI. '\n                'You can convert webpages to markdown, extract structured data using AI, '\n                'perform web searches, crawl multiple pages, and automate complex scraping workflows.',\n    tools=[\n        MCPToolset(\n            connection_params=StdioConnectionParams(\n                server_params=StdioServerParameters(\n                    command='python3',\n                    args=[\n                        SERVER_SCRIPT_PATH,\n                    ],\n                    env={\n                        'SGAI_API_KEY': os.getenv('SGAI_API_KEY'),\n                    },\n                ),\n                timeout=300.0,)\n            ),\n            # Optional: Filter which tools from the MCP server are exposed\n            # tool_filter=['scrape', 'extract', 'search']\n        )\n    ],\n)\n```\n\n### Configuration Options\n\n**Timeout Settings:**\n- Default timeout is 5 seconds, which may be too short for web scraping operations\n- Recommended: Set `timeout=300.0\n- Adjust based on your use case (crawling operations may need even longer timeouts)\n\n**Tool Filtering:**\n- By default, all registered MCP tools are exposed to the agent (see [Available Tools](#available-tools))\n- Use `tool_filter` to limit which tools are available:\n  ```python\n  tool_filter=['scrape', 'extract', 'search']\n  ```\n\n**API Key Configuration:**\n- Set via environment variable: `export SGAI_API_KEY=your-key`\n- Or pass directly in `env` dict: `'SGAI_API_KEY': 'your-key-here'`\n- Environment variable approach is recommended for security\n\n### Usage Example\n\nOnce configured, your agent can use natural language to interact with web scraping tools:\n\n```python\n# The agent can now handle queries like:\n# - \"Convert https://example.com to markdown\"\n# - \"Extract all product prices from this e-commerce page\"\n# - \"Search for recent AI research papers and summarize them\"\n# - \"Crawl this documentation site and extract all API endpoints\"\n```\nFor more information about Google ADK, visit the [official documentation](https://github.com/google/adk).\n\n## Example Use Cases\n\nThe server enables sophisticated queries across various scraping scenarios:\n\n### Single Page Scraping\n- **Markdownify**: \"Convert the ScrapeGraph documentation page to markdown\"\n- **Extract**: \"Extract all product names, prices, and ratings from this e-commerce page\"\n- **Extract with scrolling**: \"Scrape this infinite scroll page with 5 scrolls and extract all items\"\n- **Basic Scrape**: \"Fetch the HTML content of this JavaScript-heavy page with full rendering\"\n\n### Search and Research\n- **Search**: \"Research and summarize recent developments in AI-powered web scraping\"\n- **Search**: \"Search for the top 5 articles about machine learning frameworks and extract key insights\"\n- **Search**: \"Find recent news about GPT-4 and provide a structured summary\"\n- **Search**: v2 does not apply `time_range`; phrase queries to bias recency in natural language instead\n\n### Website analysis\n- Use **`crawl_start`** plus **`crawl_get_status`** to map and capture multi-page content; there is no separate **sitemap** tool on v2.\n\n### Multi-page crawling\n- **Crawl**: \"Crawl the blog in markdown mode and poll until complete\"\n- For structured fields per page, run **`extract`** on individual URLs (or **`monitor_create`** on a schedule)\n\n### Monitors and account\n- **Monitor**: \"Run this extract prompt on https://example.com every day at 9am\" (`monitor_create` with interval)\n- **Credits / history**: `credits`, `history`\n- **Agentic Scraper**: \"Execute a complex workflow: login, navigate to reports, download data, and extract summary statistics\"\n\n## Error Handling\n\nThe server implements robust error handling with detailed, actionable error messages for:\n\n- API authentication issues\n- Malformed URL structures\n- Network connectivity failures\n- Rate limiting and quota management\n\n## Common Issues\n\n### Windows-Specific Connection\n\nWhen running on Windows systems, you may need to use the following command to connect to the MCP server:\n\n```bash\nC:\\Windows\\System32\\cmd.exe /c npx -y @smithery/cli@latest run @ScrapeGraphAI/scrapegraph-mcp --config \"{\\\"scrapegraphApiKey\\\":\\\"YOUR-SGAI-API-KEY\\\"}\"\n```\n\nThis ensures proper execution in the Windows environment.\n\n### Other Common Issues\n\n**\"ScrapeGraph client not initialized\"**\n- **Cause**: Missing API key\n- **Solution**: Set `SGAI_API_KEY` environment variable or provide via `--config`\n\n**\"Error 401: Unauthorized\"**\n- **Cause**: Invalid API key\n- **Solution**: Verify your API key at the [ScrapeGraph Dashboard](https://dashboard.scrapegraphai.com)\n\n**\"Error 402: Payment Required\"**\n- **Cause**: Insufficient credits\n- **Solution**: Add credits to your ScrapeGraph account\n\n**Crawl not returning results**\n- **Cause**: Still processing (asynchronous operation)\n- **Solution**: Keep polling `crawl_get_status()` until status is \"completed\"\n\n**Tools not appearing in Claude Desktop**\n- **Cause**: Server not starting or configuration error\n- **Solution**: Check Claude logs at `~/Library/Logs/Claude/` (macOS) or `%APPDATA%\\Claude\\Logs\\` (Windows)\n\nFor detailed troubleshooting, see the [.agent documentation](.agent/README.md).\n\n## Development\n\n### Prerequisites\n\n- Python 3.13 or higher\n- pip or uv package manager\n- ScrapeGraph API key\n\n### Installation from Source\n\n```bash\n# Clone the repository\ngit clone https://github.com/ScrapeGraphAI/scrapegraph-mcp\ncd scrapegraph-mcp\n\n# Install dependencies\npip install -e \".[dev]\"\n\n# Set your API key\nexport SGAI_API_KEY=your-api-key\n\n# Run the server\nscrapegraph-mcp\n# or\npython -m scrapegraph_mcp.server\n```\n\n### Testing with MCP Inspector\n\nTest your server locally using the MCP Inspector tool:\n\n```bash\nnpx @modelcontextprotocol/inspector scrapegraph-mcp\n```\n\nThis provides a web interface to test all available tools.\n\n### Code Quality\n\n**Linting:**\n```bash\nruff check src/\n```\n\n**Type Checking:**\n```bash\nmypy src/\n```\n\n**Format Checking:**\n```bash\nruff format --check src/\n```\n\n### Project Structure\n\n```\nscrapegraph-mcp/\n├── src/\n│   └── scrapegraph_mcp/\n│       ├── __init__.py      # Package initialization\n│       └── server.py        # Main MCP server (all code in one file)\n├── .agent/                  # Developer documentation\n│   ├── README.md           # Documentation index\n│   └── system/             # System architecture docs\n├── assets/                  # Images and badges\n├── pyproject.toml          # Project metadata & dependencies\n├── smithery.yaml           # Smithery deployment config\n└── README.md               # This file\n```\n\n## Contributing\n\nWe welcome contributions! Here's how you can help:\n\n### Adding a New Tool\n\n1. **Add method to `ScapeGraphClient` class** in [server.py](src/scrapegraph_mcp/server.py):\n\n```python\ndef new_tool(self, param: str) -> Dict[str, Any]:\n    \"\"\"Tool description.\"\"\"\n    url = f\"{self.BASE_URL}/new-endpoint\"\n    data = {\"param\": param}\n    response = self.client.post(url, headers=self.headers, json=data)\n    if response.status_code != 200:\n        raise Exception(f\"Error {response.status_code}: {response.text}\")\n    return response.json()\n```\n\n2. **Add MCP tool decorator**:\n\n```python\n@mcp.tool()\ndef new_tool(param: str) -> Dict[str, Any]:\n    \"\"\"\n    Tool description for AI assistants.\n\n    Args:\n        param: Parameter description\n\n    Returns:\n        Dictionary containing results\n    \"\"\"\n    if scrapegraph_client is None:\n        return {\"error\": \"ScrapeGraph client not initialized. Please provide an API key.\"}\n\n    try:\n        return scrapegraph_client.new_tool(param)\n    except Exception as e:\n        return {\"error\": str(e)}\n```\n\n3. **Test with MCP Inspector**:\n```bash\nnpx @modelcontextprotocol/inspector scrapegraph-mcp\n```\n\n4. **Update documentation**:\n   - Add tool to this README\n   - Update [.agent documentation](.agent/README.md)\n\n5. **Submit a pull request**\n\n### Development Workflow\n\n1. Fork the repository\n2. Create a feature branch (`git checkout -b feature/amazing-feature`)\n3. Make your changes\n4. Run linting and type checking\n5. Test with MCP Inspector and Claude Desktop\n6. Update documentation\n7. Commit your changes (`git commit -m 'Add amazing feature'`)\n8. Push to the branch (`git push origin feature/amazing-feature`)\n9. Open a Pull Request\n\n### Code Style\n\n- **Line length**: 100 characters\n- **Type hints**: Required for all functions\n- **Docstrings**: Google-style docstrings\n- **Error handling**: Return error dicts, don't raise exceptions in tools\n- **Python version**: Target 3.13+\n\nFor detailed development guidelines, see the [.agent documentation](.agent/README.md).\n\n## Documentation\n\nFor comprehensive developer documentation, see:\n\n- **[.agent/README.md](.agent/README.md)** - Complete developer documentation index\n- **[.agent/system/project_architecture.md](.agent/system/project_architecture.md)** - System architecture and design\n- **[.agent/system/mcp_protocol.md](.agent/system/mcp_protocol.md)** - MCP protocol integration details\n\n## Technology Stack\n\n### Core Framework\n- **Python 3.13+** - Modern Python with type hints\n- **FastMCP** - Lightweight MCP server framework\n- **httpx 0.24.0+** - Modern async HTTP client\n\n### Development Tools\n- **Ruff** - Fast Python linter and formatter\n- **mypy** - Static type checker\n- **Hatchling** - Modern build backend\n\n### Deployment\n- **Smithery** - Automated MCP server deployment\n- **Docker** - Container support with Alpine Linux\n- **stdio transport** - Standard MCP communication\n\n### API Integration\n- **ScrapeGraph AI API** - Enterprise web scraping service\n- **Base URL**: `https://v2-api.scrapegraphai.com/api`\n- **Authentication**: API key-based\n\n## License\n\nThis project is distributed under the MIT License. For detailed terms and conditions, please refer to the LICENSE file.\n\n## Acknowledgments\n\nSpecial thanks to [tomekkorbak](https://github.com/tomekkorbak) for his implementation of [oura-mcp-server](https://github.com/tomekkorbak/oura-mcp-server), which served as starting point for this repo.\n\n## Resources\n\n### Official Links\n- [ScrapeGraph AI Homepage](https://scrapegraphai.com)\n- [ScrapeGraph Dashboard](https://dashboard.scrapegraphai.com) - Get your API key\n- [ScrapeGraph API Documentation](https://api.scrapegraphai.com/docs)\n- [GitHub Repository](https://github.com/ScrapeGraphAI/scrapegraph-mcp)\n\n### MCP Resources\n- [Model Context Protocol](https://modelcontextprotocol.io/) - Official MCP specification\n- [FastMCP Framework](https://github.com/jlowin/fastmcp) - Framework used by this server\n- [MCP Inspector](https://github.com/modelcontextprotocol/inspector) - Testing tool\n- [Smithery](https://smithery.ai/server/@ScrapeGraphAI/scrapegraph-mcp) - MCP server distribution\n- mcp-name: io.github.ScrapeGraphAI/scrapegraph-mcp\n\n### AI Assistant Integration\n- [Claude Desktop](https://claude.ai/desktop) - Desktop app with MCP support\n- [Cursor](https://cursor.sh/) - AI-powered code editor\n\n### Support\n- [GitHub Issues](https://github.com/ScrapeGraphAI/scrapegraph-mcp/issues) - Report bugs or request features\n- [Developer Documentation](.agent/README.md) - Comprehensive dev docs\n\n---\n\nMade with ❤️ by [ScrapeGraphAI](https://scrapegraphai.com) Team\n",
  "bytes": 23033,
  "sha": "356c811d6c921a418b1cd1d83830c4e4b5ea9bfea01781f0813b0bde25c63eef",
  "repo_slug": "scrapegraphai/scrapegraph-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_ai_smithery_scrapegraphai_scrapegraph_mc_f53d9663/readme"
}