web-scraping

cotdp/scraper-mcp

Context-optimized MCP server for web scraping. Reduces LLM token usage by 70-90% through server-side CSS filtering and HTML-to-markdown conversion.

6 stars

0 forks

Python

93 views

View on GitHub Add to Favorites

Installation

Option 1: Use slash command in Claude Code

/install-skill https://github.com/cotdp/scraper-mcp/tree/main/.claude/skills/web-scraping

Option 2: Clone to skills directory

# Global (all projects)

git clone https://github.com/cotdp/scraper-mcp/tree/main/.claude/skills/web-scraping ~/.claude/skills/scraper-mcp

# Project-specific

git clone https://github.com/cotdp/scraper-mcp/tree/main/.claude/skills/web-scraping .claude/skills/scraper-mcp

Add MCP server to .cursor/mcp.json:

{
  "mcpServers": {
    "skillz": {
      "command": "npx",
      "args": ["-y", "skillz-mcp", "https://github.com/cotdp/scraper-mcp/tree/main/.claude/skills/web-scraping"]
    }
  }
}

Restart Cursor after adding the configuration.

Option 1: Use Gemini CLI command

gemini extensions install https://github.com/cotdp/scraper-mcp/tree/main/.claude/skills/web-scraping

Option 2: Clone to extensions directory

git clone https://github.com/cotdp/scraper-mcp/tree/main/.claude/skills/web-scraping ~/.gemini/extensions/scraper-mcp

Topics

ai-tools context-window fastmcp llm map markdown-conversion model-context-protocol python token-optimization web-scraping