MCP (Model Context Protocol) server for Crawl4AI - Universal web crawling and data extraction. Supports STDIO, SSE, and HTTP transports.
MCP (Model Context Protocol) server for Crawl4AI - Universal web crawling and data extraction. Supports STDIO, SSE, and HTTP transports.
Integrate powerful web scraping capabilities into Claude, ChatGPT, and any MCP-compatible AI assistant.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"crawl4ai-1": {
"command": "npx",
"args": ["-y", "crawl4ai-mcp"],
"env": {
"CRAWL4AI_ENDPOINT": "your-value",
"CRAWL4AI_BEARER_TOKEN": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| CRAWL4AI_ENDPOINT | Configuration value read at startup. | Optional |
| CRAWL4AI_BEARER_TOKEN | Credential the server authenticates with. | Yes |
Retrieve public web pages as readable Markdown with the reference Fetch MCP server, including pagination for longer responses.
Use Firecrawl MCP to retrieve website content and extract information for research through Firecrawl’s API-backed web tools.
Google Trends for agents: trend verdict, stats, rising queries, regions, trending now.
Publish AI-made web pages and share files as short links from any MCP client.
Bridge to a self-hosted A-Parser: SERP, suggests and 150+ parsers via its API (read-only).
cited-mcp is an open-source Model Context Protocol server. Add it to Claude Desktop, Claude Code, Cursor or any MCP client, then ask something like: