Open-source AI web scraper with Cloudflare bypass, LLM extraction, and MCP server. Free alternative to Firecrawl & Crawl4AI.
Quick Install
Copy the config for your editor. Some servers may need additional setup — check the README.
Add to claude_desktop_config.json:
{
"mcpServers": {
"harvest": {
"command": "uvx",
"args": [
"harvest"
]
}
}
}
Run in terminal:
claude mcp add harvest uvx harvest
Add to .cursor/mcp.json:
{
"mcpServers": {
"harvest": {
"command": "uvx",
"args": [
"harvest"
]
}
}
}
Or install with pip: pip install harvest
README Excerpt
<p align="center"> <em>Scrape → P2P Cache → Semantic Search → Agent Memory</em><br> <strong>Your AI agent's persistent brain for web data.</strong> </p> <p align="center"> <a href="https://github.com/zad111ak-ai/harvest"><img src="https://img.shields.io/github/stars/zad111ak-ai/harvest?style=social" alt="GitHub Stars"></a>
Tools (10)
bc1qd8sa7e4f696wmcyszuxh9snqt2n66zrhz9g80jdenseforge_ask_whydenseforge_ingestdenseforge_searchdenseforge_statsharvest_batchharvest_contactsharvest_crawlharvest_extractharvest_scrape
Topics
ai-agentcloudflare-bypassllmmcpmcp-serveropenaiplaywrightpythonscraperweb-scraping