Scrapi MCP Server

What is Scrapi MCP Server about?

Scrapi MCP Server exposes ScrAPI’s scraping capabilities via the Model Context Protocol, allowing clients to request a URL and receive either the raw HTML or a Markdown rendering of the page. It is designed for scenarios where sites employ bot detection, captchas, or geolocation restrictions.

How to use Scrapi MCP Server?

1. Install via NPX (recommended):

   {
     "mcpServers": {
       "scrapi": {
         "command": "npx",
         "args": ["-y", "@deventerprisesoftware/scrapi-mcp"],
         "env": { "SCRAPI_API_KEY": "<YOUR_API_KEY>" }
       }
     }
   }
   

   Add the above block to your claude_desktop_config.json or any MCP‑compatible client configuration.

2. Docker alternative:

   docker run -i --rm -e SCRAPI_API_KEY=<YOUR_API_KEY> deventerprisesoftware/scrapi-mcp
   

3. Cloud SSE endpoint (no API‑key forwarding): https://api.scrapi.dev/sse.

4. Calling tools:

   • scrape_url_html – input: url (string); returns HTML.
   • scrape_url_markdown – input: url (string); returns Markdown.

Key Features

• Two tool endpoints (scrape_url_html and scrape_url_markdown).
• Handles sites with bot detection, captchas, and geo‑restrictions.
• Optional API key lifts the default limit of one concurrent call and 20 free calls per day.
• Available as a Docker image, NPX package, and hosted SSE cloud server.
• Simple integration with Claude Desktop and other MCP clients.

Use Cases

• Bypassing anti‑scraping measures: Retrieve page content from sites that block typical HTTP clients.
• Data extraction pipelines: Feed raw HTML to parsers or convert Markdown for text‑centric analysis.
• Geolocation‑specific scraping: Access region‑locked content without managing proxies.
• Rapid prototyping: Use the NPX command within a local development environment or in Claude Desktop.
• Server‑less integration: Connect to the cloud SSE endpoint for low‑maintenance deployments.

FAQ

• Do I need an API key? No, but without it you are limited to one concurrent request and 20 free calls per day.

• How do I set my API key? Pass it via the SCRAPI_API_KEY environment variable in the NPX or Docker command, or include it in the env section of your MCP configuration.

• Can I run the server locally without Docker? Yes, the NPX package downloads and runs the server directly.

• Is there a hosted version? Yes, the cloud SSE endpoint at https://api.scrapi.dev/sse.

• What output formats are supported? HTML and Markdown, selected by the respective tool.

• Will the cloud server accept my API key? Currently the cloud endpoint does not forward an API key; use the local NPX/Docker server for authenticated calls.

ScrAPI MCP Server

MCP server for using ScrAPI to scrape web pages.

ScrAPI is your ultimate web scraping solution, offering powerful, reliable, and easy-to-use features to extract data from any website effortlessly.

Tools

1. scrape_url_html

   • Use a URL to scrape a website using the ScrAPI service and retrieve the result as HTML. Use this for scraping website content that is difficult to access because of bot detection, captchas or even geolocation restrictions. The result will be in HTML which is preferable if advanced parsing is required.
   • Input: url (string)
   • Returns: HTML content of the URL

2. scrape_url_markdown

   • Use a URL to scrape a website using the ScrAPI service and retrieve the result as Markdown. Use this for scraping website content that is difficult to access because of bot detection, captchas or even geolocation restrictions. The result will be in Markdown which is preferable if the text content of the webpage is important and not the structural information of the page.
   • Input: url (string)
   • Returns: Markdown content of the URL

Setup

API Key (optional)

Optionally get an API key from the ScrAPI website.

Without an API key you will be limited to one concurrent call and twenty free calls per day with minimal queuing capabilities.

Cloud Server

The ScrAPI MCP Server is also available in the cloud over SSE at https://api.scrapi.dev/sse

Cloud MCP servers are not widely supported yet but you can access this directly from your own custom clients or use MCP Inspector to test it. There is currently no facility to pass through your API key when connecting to the cloud MCP server.

Usage with Claude Desktop

Add the following to your claude_desktop_config.json:

Docker

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

NPX

{
  "mcpServers": {
    "scrapi": {
      "command": "npx",
      "args": [
        "-y",
        "@deventerprisesoftware/scrapi-mcp"
      ],
      "env": {
        "SCRAPI_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}

Build

Docker build:

docker build -t deventerprisesoftware/scrapi-mcp -f Dockerfile .

License

This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.