mcp-webscraper
Verified Safeby samirsaci
Overview
Enables Claude Desktop to perform advanced web scraping and crawling operations, extracting structured data and analyzing website architectures through natural language.
Installation
uv run --with mcp[cli] mcp run scrapping.pySecurity Notes
The server can make arbitrary outbound network requests to user-defined URLs, which is inherent to its function. This poses a risk if controlled by a malicious prompt, potentially allowing for reconnaissance or denial-of-service attacks against internal or external targets. The code itself does not contain obvious vulnerabilities like 'eval' or hardcoded secrets. Basic rate-limiting (delay_seconds in crawl) is implemented, but user-controlled. Input URLs are validated with Pydantic's HttpUrl.
Similar Servers
claude-code-mcp
Acts as an MCP server to enable LLMs to run Claude Code CLI in one-shot mode, bypassing permissions for complex coding, file system, Git, and terminal operations.
scrapegraph-mcp
Provides AI-powered web scraping, structured data extraction, multi-page crawling, and agentic automation capabilities for language models.
scrapi-mcp
This MCP server enables AI agents to scrape web pages and retrieve their content as HTML or Markdown, with advanced browser interaction capabilities.
cortex-cloud-docs-mcp-server
Provides an MCP server for Claude and other compatible clients to search Cortex Cloud and Cortex Cloud API documentation.