The chameleon server is an AI-agent-friendly web scraping and crawling toolkit with advanced anti-bot countermeasures. It provides:

• Scrape single URL (scrape_url): Fetch and convert to Markdown/JSON, with rendering mode, proxy region, wait conditions, and structured data extraction via prompt or schema.

• Deep crawl site (crawl_site): Asynchronously crawl entire websites using BFS/DFS/Adaptive strategies, configurable depth/limits; monitor with get_job_status.

• Map website URLs (map_site): Discover all URLs on a site, optionally using sitemap only.

• Extract structured data (extract_data): Use JSON Schema to extract specific fields (prices, titles, etc.) with configurable extraction strategy.

• Search web (search_web): Perform internet searches and get results in Markdown.

• Batch scrape (batch_scrape): Concurrently fetch multiple URLs with configurable output format.

• Screenshot (get_screenshot): Capture full-page or viewport screenshots as base64 PNG.

• Diagnose anti-bot (diagnose_site): Analyze a site's anti-scraping measures and get recommended strategies.

• Check proxy (check_proxy): Verify proxy IP connectivity and exit information.

• Robots.txt (get_robots_txt): Fetch a site's robots.txt rules.

• Network log (get_network_log): Capture XHR/fetch requests for API discovery.

• Advanced anti-scraping: Automatically escalates through 6 levels of evasion techniques including UA/header spoofing, proxy rotation, TLS fingerprint simulation, and full browser rendering with behavior simulation.

All operations are designed for seamless AI agent integration.

1. Click on "Install Server".

2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.

3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@chameleon Scrape https://example.com/products and extract product names and prices as JSON"

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.