Wraps the Firecrawl API to give Claude web crawling and search capabilities through two straightforward tools. The map tool discovers all URLs on a website, while search performs web queries with optional page content retrieval. Runs as a remote server through Pipeworx's gateway, so no local setup or API keys needed in your config. You can call tools directly or use the ask_pipeworx interface to make requests in plain English and let the gateway route them. Useful when you need Claude to explore site structure or pull fresh web content without managing crawling infrastructure yourself.
Firecrawl MCP — wraps the Firecrawl API (firecrawl.dev) for web
Part of Pipeworx — an MCP gateway connecting AI agents to 737+ live data sources.
| Tool | Description |
|---|---|
map | Discover all URLs on a website |
search | Web search with optional page content |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"firecrawl": {
"url": "https://gateway.pipeworx.io/firecrawl/mcp"
}
}
}
Or connect to the full Pipeworx gateway for access to all 737+ data sources:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Instead of calling tools directly, you can ask questions in plain English:
ask_pipeworx({ question: "your question about Firecrawl data" })
The gateway picks the right tool and fills the arguments automatically.
MIT
io.github.pipeworx-io/brave-search
marcopesani/mcp-server-serper
brave/brave-search-mcp-server
com.mcparmory/google-search-console
acamolese/google-search-console-mcp
io.github.sarahpark/google-search-console