AI-native, agent-first web scraping for Python. Cost-aware tiered fetching (HTTP, browser, stealth, agent), model-agnostic LLM extraction with self-healing selector caches, API-first resolution, deterministic replay and field-level diff, and an MCP server.
View on GitHub →
Try with Claude — $10 free →
Quick Install
Copy the config for your editor. Some servers may need additional setup — check the README.
Add to claude_desktop_config.json:
{
"mcpServers": {
"scrapo": {
"command": "uvx",
"args": [
"scrapo"
]
}
}
}
Run in terminal:
claude mcp add scrapo uvx scrapo
Add to .cursor/mcp.json:
{
"mcpServers": {
"scrapo": {
"command": "uvx",
"args": [
"scrapo"
]
}
}
}
Or install with pip: pip install scrapo
Topics
agentaiai-agentsanthropiccrawlerdata-extractiongeminillmmcpmcp-serverollamaopenaiopenrouterplaywrightpydantic