Self-hosted web scraping server to scrape, crawl, extract, map, search and monitor pages without API keys.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add pyrecrawl -- uvx pyrecrawl~/.codex/config.toml
[mcp_servers.pyrecrawl]
command = "uvx"
args = ["pyrecrawl"]
# codex mcp add pyrecrawl -- uvx pyrecrawl~/.cursor/mcp.json
{
"mcpServers": {
"pyrecrawl": {
"command": "uvx",
"args": [
"pyrecrawl"
]
}
}
}.vscode/mcp.json
{
"servers": {
"pyrecrawl": {
"type": "stdio",
"command": "uvx",
"args": [
"pyrecrawl"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"pyrecrawl": {
"command": "uvx",
"args": [
"pyrecrawl"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"pyrecrawl": {
"command": "uvx",
"args": [
"pyrecrawl"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"pyrecrawl": {
"command": "uvx",
"args": [
"pyrecrawl"
]
}
}
}