ScrAPI MCP Server

What does “ScrAPI” MCP Server do?

The ScrAPI MCP Server allows AI assistants to scrape web pages by connecting to the ScrAPI service. It acts as a bridge between AI clients and external web content, enabling automated extraction of HTML or Markdown from virtually any website—even those protected by bot detection, captchas, or geolocation restrictions. This tool is useful for integrating real-time web data into AI workflows, making it ideal for developers who need up-to-date or hard-to-access web information. By exposing simple API endpoints, the ScrAPI MCP Server streamlines tasks like content gathering, data extraction, and context enrichment for Language Models, enhancing their ability to interact with and utilize live web data in various development and automation scenarios.

List of Prompts

No prompt templates are mentioned in the repository.

List of Resources

No explicit resources are listed in the repository.

List of Tools

• scrape_url_html
  • Scrapes a website using the ScrAPI service and retrieves the result as HTML. Useful when advanced parsing or structural information is needed from web content that is hard to access.
• scrape_url_markdown
  • Scrapes a website using the ScrAPI service and retrieves the result as Markdown. Suitable when the text content of the web page is important, rather than its structure.

Use Cases of this MCP Server

• Automated Content Extraction
  • Developers can automate the process of extracting either the HTML or Markdown content from web pages, even those protected by anti-bot measures.
• Data Enrichment for LLMs
  • Enhance AI model responses by supplying up-to-date web content as context, improving accuracy and relevance.
• Competitive and Market Analysis
  • Quickly gather data from competitor sites or market sources that are otherwise challenging to scrape due to technical barriers.
• Content Monitoring
  • Set up monitoring solutions that regularly pull and analyze changes from specific websites for compliance, updates, or news alerts.
• Research Automation
  • Streamline academic or market research by programmatically collecting web-based information and converting it into usable formats for analysis.

How to set it up

Windsurf

No specific instructions for Windsurf are provided in the repository.

Claude

1. Obtain an optional API key from https://scrapi.tech (recommended for higher usage limits).
2. Open your claude_desktop_config.json file.
3. Add the ScrAPI MCP Server using the Docker configuration below.
4. Save the file and restart Claude Desktop.
5. Verify setup by checking for successful tool usage in the Claude interface.

Example JSON:

{
  "mcpServers": {
    "scrapi": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "SCRAPI_API_KEY",
        "deventerprisesoftware/scrapi-mcp"
      ],
      "env": {
        "SCRAPI_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}

Securing API keys:
Place your API key in the env section as shown above, instead of hard-coding it.

Cursor

No specific instructions for Cursor are provided in the repository.

Cline

No specific instructions for Cline are provided in the repository.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "scrapi": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “scrapi” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the two tables above, the ScrAPI MCP server is straightforward, focused, and production-ready for its core function (web scraping), but lacks advanced MCP features (like resources, sampling, or roots) and broader platform documentation. Its value is high for web scraping use-cases, but limited if you need advanced MCP primitives or many prompt workflows.

MCP Score

Overall rating: 6/10
The ScrAPI MCP Server covers the basics of tool exposure and secure setup, but lacks depth in prompt/resource support and cross-platform setup documentation. Great for its specific use, but not a “full-stack” MCP solution.