ScrapeGraph MCP Server
A production-ready Model Context Protocol server that enables language models to leverage AI-powered web scraping capabilities, offering tools for transforming webpages to markdown, extracting structured data, and executing AI-powered web searches.
README Documentation
ScrapeGraph MCP Server
A production-ready Model Context Protocol (MCP) server that provides seamless integration with the ScrapeGraph AI API. This server enables language models to leverage advanced AI-powered web scraping capabilities with enterprise-grade reliability.
Table of Contents
- Key Features
- Quick Start
- Available Tools
- Setup Instructions
- Local Usage
- Google ADK Integration
- Example Use Cases
- Error Handling
- Common Issues
- Development
- Contributing
- Documentation
- Technology Stack
- License
Key Features
- 8 Powerful Tools: From simple markdown conversion to complex multi-page crawling and agentic workflows
- AI-Powered Extraction: Intelligently extract structured data using natural language prompts
- Multi-Page Crawling: SmartCrawler supports asynchronous crawling with configurable depth and page limits
- Infinite Scroll Support: Handle dynamic content loading with configurable scroll counts
- JavaScript Rendering: Full support for JavaScript-heavy websites
- Flexible Output Formats: Get results as markdown, structured JSON, or custom schemas
- Easy Integration: Works seamlessly with Claude Desktop, Cursor, and any MCP-compatible client
- Enterprise-Ready: Robust error handling, timeout management, and production-tested reliability
- Simple Deployment: One-command installation via Smithery or manual setup
- Comprehensive Documentation: Detailed developer docs in
.agent/folder
Quick Start
1. Get Your API Key
Sign up and get your API key from the ScrapeGraph Dashboard
2. Install with Smithery (Recommended)
npx -y @smithery/cli install @ScrapeGraphAI/scrapegraph-mcp --client claude
3. Start Using
Ask Claude or Cursor:
- "Convert https://scrapegraphai.com to markdown"
- "Extract all product prices from this e-commerce page"
- "Research the latest AI developments and summarize findings"
That's it! The server is now available to your AI assistant.
Available Tools
The server provides 8 enterprise-ready tools for AI-powered web scraping:
Core Scraping Tools
1. markdownify
Transform any webpage into clean, structured markdown format.
markdownify(website_url: str)
- Credits: 2 per request
- Use case: Quick webpage content extraction in markdown
2. smartscraper
Leverage AI to extract structured data from any webpage with support for infinite scrolling.
smartscraper(
user_prompt: str,
website_url: str,
number_of_scrolls: int = None,
markdown_only: bool = None
)
- Credits: 10+ (base) + variable based on scrolling
- Use case: AI-powered data extraction with custom prompts
3. searchscraper
Execute AI-powered web searches with structured, actionable results.
searchscraper(
user_prompt: str,
num_results: int = None,
number_of_scrolls: int = None
)
- Credits: Variable (3-20 websites × 10 credits)
- Use case: Multi-source research and data aggregation
Advanced Scraping Tools
4. scrape
Basic scraping endpoint to fetch page content with optional heavy JavaScript rendering.
scrape(website_url: str, render_heavy_js: bool = None)
- Use case: Simple page content fetching with JS rendering support
5. sitemap
Extract sitemap URLs and structure for any website.
sitemap(website_url: str)
- Use case: Website structure analysis and URL discovery
Multi-Page Crawling
6. smartcrawler_initiate
Initiate intelligent multi-page web crawling (asynchronous operation).
smartcrawler_initiate(
url: str,
prompt: str = None,
extraction_mode: str = "ai",
depth: int = None,
max_pages: int = None,
same_domain_only: bool = None
)
- AI Extraction Mode: 10 credits per page - extracts structured data
- Markdown Mode: 2 credits per page - converts to markdown
- Returns:
request_idfor polling - Use case: Large-scale website crawling and data extraction
7. smartcrawler_fetch_results
Retrieve results from asynchronous crawling operations.
smartcrawler_fetch_results(request_id: str)
- Returns: Status and results when crawling is complete
- Use case: Poll for crawl completion and retrieve results
Intelligent Agent-Based Scraping
8. agentic_scrapper
Run advanced agentic scraping workflows with customizable steps and structured output schemas.
agentic_scrapper(
url: str,
user_prompt: str = None,
output_schema: dict = None,
steps: list = None,
ai_extraction: bool = None,
persistent_session: bool = None,
timeout_seconds: float = None
)
- Use case: Complex multi-step workflows with custom schemas and persistent sessions
Setup Instructions
To utilize this server, you'll need a ScrapeGraph API key. Follow these steps to obtain one:
- Navigate to the ScrapeGraph Dashboard
- Create an account and generate your API key
Automated Installation via Smithery
For automated installation of the ScrapeGraph API Integration Server using Smithery:
npx -y @smithery/cli install @ScrapeGraphAI/scrapegraph-mcp --client claude
Claude Desktop Configuration
Update your Claude Desktop configuration file with the following settings (located on the top rigth of the Cursor page):
(remember to add your API key inside the config)
{
"mcpServers": {
"@ScrapeGraphAI-scrapegraph-mcp": {
"command": "npx",
"args": [
"-y",
"@smithery/cli@latest",
"run",
"@ScrapeGraphAI/scrapegraph-mcp",
"--config",
"\"{\\\"scrapegraphApiKey\\\":\\\"YOUR-SGAI-API-KEY\\\"}\""
]
}
}
}
The configuration file is located at:
- Windows:
%APPDATA%/Claude/claude_desktop_config.json - macOS:
~/Library/Application\ Support/Claude/claude_desktop_config.json
Cursor Integration
Add the ScrapeGraphAI MCP server on the settings:

Local Usage
To run the MCP server locally for development or testing, follow these steps:
Prerequisites
- Python 3.13 or higher
- pip or uv package manager
- ScrapeGraph API key
Installation
- Clone the repository (if you haven't already):
git clone https://github.com/ScrapeGraphAI/scrapegraph-mcp
cd scrapegraph-mcp
- Install the package:
# Using pip
pip install -e .
# Or using uv (faster)
uv pip install -e .
- Set your API key:
# macOS/Linux
export SGAI_API_KEY=your-api-key-here
# Windows (PowerShell)
$env:SGAI_API_KEY="your-api-key-here"
# Windows (CMD)
set SGAI_API_KEY=your-api-key-here
Running the Server Locally
You can run the server directly:
# Using the installed command
scrapegraph-mcp
# Or using Python module
python -m scrapegraph_mcp.server
The server will start and communicate via stdio (standard input/output), which is the standard MCP transport method.
Testing with MCP Inspector
Test your local server using the MCP Inspector tool:
npx @modelcontextprotocol/inspector python -m scrapegraph_mcp.server
This provides a web interface to test all available tools interactively.
Configuring Claude Desktop for Local Server
To use your locally running server with Claude Desktop, update your configuration file:
macOS/Linux (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"scrapegraph-mcp-local": {
"command": "python",
"args": [
"-m",
"scrapegraph_mcp.server"
],
"env": {
"SGAI_API_KEY": "your-api-key-here"
}
}
}
}
Windows (%APPDATA%\Claude\claude_desktop_config.json):
{
"mcpServers": {
"scrapegraph-mcp-local": {
"command": "python",
"args": [
"-m",
"scrapegraph_mcp.server"
],
"env": {
"SGAI_API_KEY": "your-api-key-here"
}
}
}
}
Note: Make sure Python is in your PATH. You can verify by running python --version in your terminal.
Configuring Cursor for Local Server
In Cursor's MCP settings, add a new server with:
- Command:
python - Args:
["-m", "scrapegraph_mcp.server"] - Environment Variables:
{"SGAI_API_KEY": "your-api-key-here"}
Troubleshooting Local Setup
Server not starting:
- Verify Python is installed:
python --version - Check that the package is installed:
pip list | grep scrapegraph-mcp - Ensure API key is set:
echo $SGAI_API_KEY(macOS/Linux) orecho %SGAI_API_KEY%(Windows)
Tools not appearing:
- Check Claude Desktop logs:
- macOS:
~/Library/Logs/Claude/ - Windows:
%APPDATA%\Claude\Logs\
- macOS:
- Verify the server starts without errors when run directly
- Check that the configuration JSON is valid
Import errors:
- Reinstall the package:
pip install -e . --force-reinstall - Verify dependencies:
pip install -r requirements.txt(if available)
Google ADK Integration
The ScrapeGraph MCP server can be integrated with Google ADK (Agent Development Kit) to create AI agents with web scraping capabilities.
Prerequisites
- Python 3.13 or higher
- Google ADK installed
- ScrapeGraph API key
Installation
- Install Google ADK (if not already installed):
pip install google-adk
- Set your API key:
export SGAI_API_KEY=your-api-key-here
Basic Integration Example
Create an agent file (e.g., agent.py) with the following configuration:
import os
from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import MCPToolset
from google.adk.tools.mcp_tool.mcp_session_manager import StdioConnectionParams
from mcp import StdioServerParameters
# Path to the scrapegraph-mcp server directory
SCRAPEGRAPH_MCP_PATH = "/path/to/scrapegraph-mcp"
# Path to the server.py file
SERVER_SCRIPT_PATH = os.path.join(
SCRAPEGRAPH_MCP_PATH,
"src",
"scrapegraph_mcp",
"server.py"
)
root_agent = LlmAgent(
model='gemini-2.0-flash',
name='scrapegraph_assistant_agent',
instruction='Help the user with web scraping and data extraction using ScrapeGraph AI. '
'You can convert webpages to markdown, extract structured data using AI, '
'perform web searches, crawl multiple pages, and automate complex scraping workflows.',
tools=[
MCPToolset(
connection_params=StdioConnectionParams(
server_params=StdioServerParameters(
command='python3',
args=[
SERVER_SCRIPT_PATH,
],
env={
'SGAI_API_KEY': os.getenv('SGAI_API_KEY'),
},
),
timeout=300.0,)
),
# Optional: Filter which tools from the MCP server are exposed
# tool_filter=['markdownify', 'smartscraper', 'searchscraper']
)
],
)
Configuration Options
Timeout Settings:
- Default timeout is 5 seconds, which may be too short for web scraping operations
- Recommended: Set `timeout=300.0
- Adjust based on your use case (crawling operations may need even longer timeouts)
Tool Filtering:
- By default, all 8 tools are exposed to the agent
- Use
tool_filterto limit which tools are available:tool_filter=['markdownify', 'smartscraper', 'searchscraper']
API Key Configuration:
- Set via environment variable:
export SGAI_API_KEY=your-key - Or pass directly in
envdict:'SGAI_API_KEY': 'your-key-here' - Environment variable approach is recommended for security
Usage Example
Once configured, your agent can use natural language to interact with web scraping tools:
# The agent can now handle queries like:
# - "Convert https://example.com to markdown"
# - "Extract all product prices from this e-commerce page"
# - "Search for recent AI research papers and summarize them"
# - "Crawl this documentation site and extract all API endpoints"
For more information about Google ADK, visit the official documentation.
Example Use Cases
The server enables sophisticated queries across various scraping scenarios:
Single Page Scraping
- Markdownify: "Convert the ScrapeGraph documentation page to markdown"
- SmartScraper: "Extract all product names, prices, and ratings from this e-commerce page"
- SmartScraper with scrolling: "Scrape this infinite scroll page with 5 scrolls and extract all items"
- Basic Scrape: "Fetch the HTML content of this JavaScript-heavy page with full rendering"
Search and Research
- SearchScraper: "Research and summarize recent developments in AI-powered web scraping"
- SearchScraper: "Search for the top 5 articles about machine learning frameworks and extract key insights"
- SearchScraper: "Find recent news about GPT-4 and provide a structured summary"
Website Analysis
- Sitemap: "Extract the complete sitemap structure from the ScrapeGraph website"
- Sitemap: "Discover all URLs on this blog site"
Multi-Page Crawling
- SmartCrawler (AI mode): "Crawl the entire documentation site and extract all API endpoints with descriptions"
- SmartCrawler (Markdown mode): "Convert all pages in the blog to markdown up to 2 levels deep"
- SmartCrawler: "Extract all product information from an e-commerce site, maximum 100 pages, same domain only"
Advanced Agentic Scraping
- Agentic Scraper: "Navigate through a multi-step authentication form and extract user dashboard data"
- Agentic Scraper with schema: "Follow pagination links and compile a dataset with schema: {title, author, date, content}"
- Agentic Scraper: "Execute a complex workflow: login, navigate to reports, download data, and extract summary statistics"
Error Handling
The server implements robust error handling with detailed, actionable error messages for:
- API authentication issues
- Malformed URL structures
- Network connectivity failures
- Rate limiting and quota management
Common Issues
Windows-Specific Connection
When running on Windows systems, you may need to use the following command to connect to the MCP server:
C:\Windows\System32\cmd.exe /c npx -y @smithery/cli@latest run @ScrapeGraphAI/scrapegraph-mcp --config "{\"scrapegraphApiKey\":\"YOUR-SGAI-API-KEY\"}"
This ensures proper execution in the Windows environment.
Other Common Issues
"ScrapeGraph client not initialized"
- Cause: Missing API key
- Solution: Set
SGAI_API_KEYenvironment variable or provide via--config
"Error 401: Unauthorized"
- Cause: Invalid API key
- Solution: Verify your API key at the ScrapeGraph Dashboard
"Error 402: Payment Required"
- Cause: Insufficient credits
- Solution: Add credits to your ScrapeGraph account
SmartCrawler not returning results
- Cause: Still processing (asynchronous operation)
- Solution: Keep polling
smartcrawler_fetch_results()until status is "completed"
Tools not appearing in Claude Desktop
- Cause: Server not starting or configuration error
- Solution: Check Claude logs at
~/Library/Logs/Claude/(macOS) or%APPDATA%\Claude\Logs\(Windows)
For detailed troubleshooting, see the .agent documentation.
Development
Prerequisites
- Python 3.13 or higher
- pip or uv package manager
- ScrapeGraph API key
Installation from Source
# Clone the repository
git clone https://github.com/ScrapeGraphAI/scrapegraph-mcp
cd scrapegraph-mcp
# Install dependencies
pip install -e ".[dev]"
# Set your API key
export SGAI_API_KEY=your-api-key
# Run the server
scrapegraph-mcp
# or
python -m scrapegraph_mcp.server
Testing with MCP Inspector
Test your server locally using the MCP Inspector tool:
npx @modelcontextprotocol/inspector scrapegraph-mcp
This provides a web interface to test all available tools.
Code Quality
Linting:
ruff check src/
Type Checking:
mypy src/
Format Checking:
ruff format --check src/
Project Structure
scrapegraph-mcp/
├── src/
│ └── scrapegraph_mcp/
│ ├── __init__.py # Package initialization
│ └── server.py # Main MCP server (all code in one file)
├── .agent/ # Developer documentation
│ ├── README.md # Documentation index
│ └── system/ # System architecture docs
├── assets/ # Images and badges
├── pyproject.toml # Project metadata & dependencies
├── smithery.yaml # Smithery deployment config
└── README.md # This file
Contributing
We welcome contributions! Here's how you can help:
Adding a New Tool
- Add method to
ScapeGraphClientclass in server.py:
def new_tool(self, param: str) -> Dict[str, Any]:
"""Tool description."""
url = f"{self.BASE_URL}/new-endpoint"
data = {"param": param}
response = self.client.post(url, headers=self.headers, json=data)
if response.status_code != 200:
raise Exception(f"Error {response.status_code}: {response.text}")
return response.json()
- Add MCP tool decorator:
@mcp.tool()
def new_tool(param: str) -> Dict[str, Any]:
"""
Tool description for AI assistants.
Args:
param: Parameter description
Returns:
Dictionary containing results
"""
if scrapegraph_client is None:
return {"error": "ScrapeGraph client not initialized. Please provide an API key."}
try:
return scrapegraph_client.new_tool(param)
except Exception as e:
return {"error": str(e)}
- Test with MCP Inspector:
npx @modelcontextprotocol/inspector scrapegraph-mcp
-
Update documentation:
- Add tool to this README
- Update .agent documentation
-
Submit a pull request
Development Workflow
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature) - Make your changes
- Run linting and type checking
- Test with MCP Inspector and Claude Desktop
- Update documentation
- Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
Code Style
- Line length: 100 characters
- Type hints: Required for all functions
- Docstrings: Google-style docstrings
- Error handling: Return error dicts, don't raise exceptions in tools
- Python version: Target 3.13+
For detailed development guidelines, see the .agent documentation.
Documentation
For comprehensive developer documentation, see:
- .agent/README.md - Complete developer documentation index
- .agent/system/project_architecture.md - System architecture and design
- .agent/system/mcp_protocol.md - MCP protocol integration details
Technology Stack
Core Framework
- Python 3.13+ - Modern Python with type hints
- FastMCP - Lightweight MCP server framework
- httpx 0.24.0+ - Modern async HTTP client
Development Tools
- Ruff - Fast Python linter and formatter
- mypy - Static type checker
- Hatchling - Modern build backend
Deployment
- Smithery - Automated MCP server deployment
- Docker - Container support with Alpine Linux
- stdio transport - Standard MCP communication
API Integration
- ScrapeGraph AI API - Enterprise web scraping service
- Base URL:
https://api.scrapegraphai.com/v1 - Authentication: API key-based
License
This project is distributed under the MIT License. For detailed terms and conditions, please refer to the LICENSE file.
Acknowledgments
Special thanks to tomekkorbak for his implementation of oura-mcp-server, which served as starting point for this repo.
Resources
Official Links
- ScrapeGraph AI Homepage
- ScrapeGraph Dashboard - Get your API key
- ScrapeGraph API Documentation
- GitHub Repository
MCP Resources
- Model Context Protocol - Official MCP specification
- FastMCP Framework - Framework used by this server
- MCP Inspector - Testing tool
- Smithery - MCP server distribution
- mcp-name: io.github.ScrapeGraphAI/scrapegraph-mcp
AI Assistant Integration
- Claude Desktop - Desktop app with MCP support
- Cursor - AI-powered code editor
Support
- GitHub Issues - Report bugs or request features
- Developer Documentation - Comprehensive dev docs
Made with ❤️ by ScrapeGraphAI Team