The ScrAPI MCP Server is a web scraping tool that extracts data from websites while overcoming common restrictions like bot detection, captchas, and geolocation blocks. It offers two main scraping modes: HTML format for advanced parsing when structural information is needed, and Markdown format for text-focused extraction. The server supports API key customization for enhanced usage limits, can be deployed locally (via Docker or NPX) or in the cloud (via SSE or HTTP), and integrates seamlessly with Claude Desktop.
Enables running the ScrAPI MCP server in a containerized environment with a pre-built Docker image for easy deployment
Converts scraped web content into Markdown format, ideal when text content of a webpage is important rather than structural information
Provides package distribution through npm registry, allowing the server to be installed and run via npx
Displays status badges for license, npm downloads, and Docker pulls to indicate the project's activity and adoption
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., "@ScrAPI MCP Serverscrape the product page from that e-commerce site with bot protection 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.
![]()
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
scrape_url_htmlUse 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.
Inputs:
url(string, required): The URL to scrapebrowserCommands(string, optional): JSON array of browser commands to execute before scraping
Returns: HTML content of the URL
scrape_url_markdownUse 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.
Inputs:
url(string, required): The URL to scrapebrowserCommands(string, optional): JSON array of browser commands to execute before scraping
Returns: Markdown content of the URL
Related MCP server: MD Webcrawl MCP
Browser Commands
Both tools support optional browser commands that allow you to interact with the page before scraping. This is useful for:
Clicking buttons (e.g., "Accept Cookies", "Load More")
Filling out forms
Selecting dropdown options
Scrolling to load dynamic content
Waiting for elements to appear
Executing custom JavaScript
Available Commands
Commands are provided as a JSON array string. All commands are executed with human-like behavior (random mouse movements, variable typing speed, etc.):
Command | Format | Description |
Click |
| Click an element using CSS selector |
Input |
| Fill an input field |
Select |
| Select from dropdown (by value or text) |
Scroll |
| Scroll down by pixels (negative values scroll up) |
Wait |
| Wait for milliseconds (max 15000) |
WaitFor |
| Wait for element to appear in DOM |
JavaScript |
| Execute custom JavaScript code |
Example Usage
Finding CSS Selectors
Need help finding CSS selectors? Try the Rayrun browser extension to easily select elements and generate selectors.
For more details, see the Browser Commands documentation.
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.tech/mcp/sse and streamable HTTP at https://api.scrapi.tech/mcp
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
NPX

Build
Docker build:
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.