AnyCrawl MCP Server, with Scrape, Crawl and SERP.
AnyCrawl MCP Server, with Scrape, Crawl and SERP.
🚀 AnyCrawl MCP Server — Powerful web scraping and crawling for Cursor, Claude, and other LLM clients via the Model Context Protocol (MCP).
AnyCrawl is a powerful Node.js/TypeScript crawler that turns websites into LLM-ready data and extracts structured SERP results from Google/Bing/Baidu/etc. It features native multi-threading for bulk processing and supports multiple output formats.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"mcp-server-anycrawl": {
"command": "npx",
"args": ["-y", "anycrawl-mcp"],
"env": {
"ANYCRAWL_API_KEY": "YOUR_API_KEY"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| ANYCRAWL_API_KEY | Credential the server authenticates with. | Yes |
| ANYCRAWL_BASE_URL | Endpoint or connection string the server talks to. | Yes |
| ANYCRAWL_HOST | Endpoint or connection string the server talks to. | Optional |
| ANYCRAWL_PORT | Configuration value read at startup. | Optional |
| LOG_LEVEL | Configuration value read at startup. | Optional |
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.
A remote Model Context Protocol server that gives AI agents 26 tools for reading and checking the web — no browser, no setup, pay only for successful calls.
Marginalia MCP — independent web search over a non-commercial, non-SEO index.
looot is one gateway to about 2,500 data provider operations: email find and verify, company enrichment, SEO and SERP data, social profiles, web scraping and more. One token, one prepaid balance…
Bing Webmaster, IndexNow and Google Search Console for AI: rankings, indexing gaps, AI crawlers.