Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Thordata MCP Serverscrape product details from amazon.com and output as markdown"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
π Overview
ScraperMCP server seamlessly bridges AI and web ecosystems, providing one-click access to any website worldwide, real-time JavaScript rendering, intelligent anti-crawling mechanism bypass, and outputting AI-ready structured data content.
π οΈ MCP Tools
Thordata MCP supports dual-channel data acquisition through unlocker and regular proxies, fully compatible with multiple data formats including MarkDown, HTML, and Links.
Web Scraper API Tool
Thordata MCP provides the parse_with_ai_selectors tool, leveraging Thordata Web Scraper API to implement intelligent scraping of any website.
β Prerequisites
Before deployment, please ensure you have:
Thordata Web Scraper API Account: Visit thordata to obtain your exclusive username and password;
π¦ Configuration
Environment Variables
Thordata MCP server supports the following environment variable configurations:
Name | Description | Default Value |
| Unlocker username | |
| Unlocker password | |
| Unlocker proxy address | |
| Regular proxy username | |
| Regular proxy password | |
| Regular proxy address |
Using uv Configuration
Install uv package manager:
# macOS and Linux curl -LsSf https://astral.sh/uv/install.sh | shOr:
# Windows powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"Use the following configuration:
{ "mcpServers": { "Scraper": { "command": "uv", "args": [ "--directory", "<absolute folder path>", # e.g., D:\\ScraperMcp "run", "Scraper.py" ] } }
}
### Startup Command
fastmcp run Scraper.py:mcp
### π₯οΈ Manual Setup Guide
#### Claude Desktop Configuration
1. Open Claude application
2. Navigate to **Settings β Developer β Edit Configuration**
3. Add the above configuration to the `claude_desktop_config.json` file
#### Cursor AI Configuration
1. Open Cursor editor
2. Navigate to **Settings β Cursor Settings β MCP**
3. Click **Add New Global MCP Server**
4. Configure corresponding parameters
#### Cline Configuration
1. Open Cline settings
2. Navigate to **MCP Server Settings β Installed**
3. Click **Configure MCP Server**
4. Configure corresponding parameters
### Manual Setup: Cline Settings β MCP Server Settings β Installed β Click Configure MCP Server and configure corresponding parameters
## π‘οΈ License
Open source distribution under MIT License - see [LICENSE](LICENSE) file for details.
---
## About Thordata
Thordata, as a market-leading web intelligence collection platform, adheres to the highest business ethics and compliance standards, empowering global enterprises to uncover data-driven business insights.
<div align="center">
<sub>
Made by <a href="https://www.thordata.com/">Thordata</a>, if MCP saves you valuable time, we invite you to give β support.
</sub>
</div>
## β¨ Core Features
<details>
<summary><strong>Global Website Content Scraping</strong></summary>
<br>
- Supports data extraction from any URL, including complex single-page applications
- Complete JavaScript rendering capability, ensuring perfect presentation of dynamic content
- Flexible rendering mode selection: full JS rendering, pure HTML, or no rendering
</details>
<details>
<summary><strong>Intelligent AI Data Preprocessing</strong></summary>
<br>
- Automated HTML cleaning and conversion to highly readable Markdown
- Intelligent extraction of valid and usable links, optimizing data structure
- Native HTML format support, maintaining data integrity
</details>
<details>
<summary><strong>Global Network Barrier-Free Access</strong></summary>
<br>
- Efficiently bypasses complex anti-crawling protection systems
- Stable scraping of high-difficulty website content
- 195+ country IP pool automatic rotation, breaking geographical restrictions
</details>
<details>
<summary><strong>Cross-Platform Flexible Deployment</strong></summary>
<br>
- Customizable rendering and parsing parameter configuration
- Seamless integration with AI models and analysis tools
- Full support for macOS, Windows, and Linux systems
</details>
---
## Why Choose Thordata MCP? πΈοΈ β π¦ β π€
Just tell the LLM *"Summarize the latest discussions about MCP on Hacker News"* and get precise answers immediately.
MCP (Multi-Client Protocol) handles all the tedious steps for you:
| Thordata MCP Core Value | Benefits for You |
|-------------------------------------------------------------------|-------------------------------------------|
| **Thordata global proxy network intelligently bypasses anti-bot detection** | Ensures access availability and identity anonymity |
| **One-click data acquisition solution** | Easily handles complex single-page applications |
| **Multi-format output support (MarkDown/HTML/Links)** | Precisely matches your data requirements |This server cannot be installed
Resources
Looking for Admin?
Admins can modify the Dockerfile, update the server description, and track usage metrics. If you are the server author, to access the admin panel.