Firecrawl for
Google Cloud

Give Gemini and ADK agents data from the web and beyond.
Reach the live web and 100+ official data providers in Firecrawl Alexandria.

//
Used by over 1.25M developers
//
Trusted by 150,000+
companies
of all sizes
[ 01 / 04 ]
·
Features

Perfect for

Give Gemini agents structured data from official providers in Firecrawl Alexandria
Buy Firecrawl through Google Cloud Marketplace and pay on your Google Cloud bill
Scrape web pages into clean markdown and pass them to Gemini
Build Agent Development Kit (ADK) agents that search, scrape, and crawl the web
Add web search and scraping to Gemini CLI and Antigravity

Key Features

Pull structured records from 100+ official data providers in Firecrawl Alexandria
Find data tools in Firecrawl Alexandria, check their inputs and price, then run them
Listed on Google Cloud Marketplace and sold through private offers
Google Cloud handles billing for Marketplace purchases
A private offer can draw down your existing Google Cloud spend commitment
Scrape any URL into clean markdown or structured JSON for Gemini
Connect ADK agents to the Firecrawl MCP server over streamable HTTP
Search, scrape, map, crawl, and Firecrawl Alexandria tools for your ADK agents
Keyless Search, Scrape, and Parse in Gemini CLI and Antigravity through the hosted MCP server
Works with self-hosted Firecrawl through FIRECRAWL_API_URL
Enterprise plans include zero data retention, dedicated support with an SLA, and custom concurrent browsers
[ 02 / 04 ]
·
Installation

Use Firecrawl with Google Cloud

Choose how you buy Firecrawl, then connect it to the Google tools you build with.

1

Choose how to buy

Start on a self-serve plan, or buy through Google Cloud Marketplace. For Marketplace, contact our team with your volume and requirements. We send a private offer to your Google Cloud billing account, and you accept it in the Google Cloud console.

2

Get your API key

Sign up and copy your API key from the dashboard. Set it as FIRECRAWL_API_KEY in the environment your code runs in.

3

Connect Gemini

Scrape a page with the Firecrawl SDK and pass the markdown to Gemini with the Google Gen AI SDK.

Scrape a page and summarize it with Gemini
// npm install firecrawl @google/genai
import { Firecrawl } from "firecrawl";
import { GoogleGenAI } from "@google/genai";

const firecrawl = new Firecrawl({ apiKey: process.env.FIRECRAWL_API_KEY });
const ai = new GoogleGenAI({ apiKey: process.env.GEMINI_API_KEY });

const page = await firecrawl.scrape("https://firecrawl.dev", { formats: ["markdown"] });

const response = await ai.models.generateContent({
  model: "gemini-2.5-flash",
  contents: `Summarize: ${page.markdown}`,
});

console.log(response.text);
4

Give ADK agents web and Alexandria tools

Add the Firecrawl MCP server to your agent as an MCPToolset. The agent gets tools to scrape, map, search, and crawl, and to find and run data providers in Firecrawl Alexandria.

ADK agent with Firecrawl tools
import os

from google.adk.agents.llm_agent import Agent
from google.adk.tools.mcp_tool.mcp_session_manager import StreamableHTTPServerParams
from google.adk.tools.mcp_tool.mcp_toolset import MCPToolset

root_agent = Agent(
    model="gemini-2.5-pro",
    name="firecrawl_agent",
    instruction="Help the user search for website content",
    tools=[
        MCPToolset(
            connection_params=StreamableHTTPServerParams(
                url="https://mcp.firecrawl.dev/v2/mcp",
                headers={"Authorization": f"Bearer {os.environ['FIRECRAWL_API_KEY']}"},
            ),
        )
    ],
)
5

Add Firecrawl to Gemini CLI

Add the hosted MCP server to ~/.gemini/settings.json, restart Gemini CLI, and run /mcp list to confirm the Firecrawl tools are available.

~/.gemini/settings.json
{
  "mcpServers": {
    "firecrawl": {
      "httpUrl": "https://mcp.firecrawl.dev/v2/mcp"
    }
  }
}
[ 03 / 04 ]
·
What Our Customers Say
//
Community
//

People love
building with Firecrawl

Discover why developers choose Firecrawl every day.
//
FAQ
//

Frequently
asked questions

Everything you need to know about this integration.
General
Firecrawl Alexandria is Firecrawl's library of data for AI agents, with 100+ official data providers alongside Firecrawl's own specialized indexes and the live web. When a Gemini or ADK agent needs data the open web covers poorly, it searches Alexandria for a tool that fits, checks what the tool needs, then runs it and gets structured data straight from the source. Discovery is free, and each tool lists its price. Some providers require your organization to accept their terms first, which an admin can do in the Firecrawl dashboard.
Yes. Firecrawl is listed on Google Cloud Marketplace and is sold there through private offers. Contact our sales team to get one. Google Cloud handles billing for Marketplace purchases.
Technical
Contact our sales team with your Google Cloud billing account and what you need. A private offer sets your plan, credit volume, price, and contract length. We send it to that account, and you accept it in the Google Cloud console. Charges then appear on your Google Cloud bill.
Yes. The listing is sold by Firecrawl and gives you the same hosted API, SDKs, MCP server, CLI, and access to Firecrawl Alexandria.
Integration
It can. Firecrawl runs on Google Cloud, so if your team has a Google Cloud spend commitment, buying Firecrawl through a private offer can draw down against it. Google sets which purchases qualify, so confirm the terms of your agreement with your Google account team. Promotional and startup credits can't be used on third-party Marketplace purchases.
Yes. Scrape a page with the Firecrawl SDK and pass the markdown to Gemini with the Google Gen AI SDK. The Firecrawl docs show how to summarize a page, analyze it over a multi-turn chat, and extract structured data with Gemini's JSON mode.
Advanced
Add the Firecrawl MCP server to your agent as an MCPToolset. Connect to the remote server at https://mcp.firecrawl.dev/v2/mcp with your API key, or run the firecrawl-mcp package locally. Your agent gets tools to scrape, map, search, and crawl. On the remote server, it can also find and run official data providers in Firecrawl Alexandria.
Not to start. The hosted MCP server gives keyless access to Search, Scrape, and Parse, with limits shared by users on the same public IP. Sign in or add an API key for the full set of tools and for unattended use.
More Questions 1
Yes. When you run the Firecrawl MCP server locally, set FIRECRAWL_API_URL to your instance's URL and requests go there instead of the cloud API.
Why Firecrawl?
The world's most comprehensive web data API. Our custom browser stack and semantic index deliver superior data quality across any website, handling more content types and edge cases than any competitor.
JavaScript rendering, dynamic content, and robust request handling built-in.
Process millions of pages with automatic rate limiting, caching, and distributed infrastructure.
Optimized scraping engine with parallel processing and smart caching for instant results.
Comprehensive docs, SDKs for all major languages, and dedicated support to help you succeed.
[ 04 / 04 ]
·
Pricing

Flexible pricing

Start for free, then scale as you grow.

Free Plan

A lightweight way to get started.
No cost, no card, no hassle.
$0
/month
500 searches or 1,000 pages scraped
2 concurrent requests
Low rate limits

Hobby

Great for side projects and small tools.
Fast, simple, no overkill.
$16
/month
Billed yearly
Save $38
2,500 searches or 5,000 pages scraped
5 concurrent requests
Basic support
$9 per extra 1.5k credits

Standard
Most popular

Perfect for scaling with less effort.
Simple, solid, dependable.
$83
/month
Billed yearly
Save $198
50,000 searches or 100,000 pages scraped
25 concurrent requests
Standard support
$47 per extra 35k credits

Growth

Built for high volume and speed.
Firecrawl at full force.
$333
/month
Billed yearly
Save $798
250,000 searches or 500,000 pages scraped
50 concurrent requests
Priority support
$177 per extra 175k credits

Scale Plans

High-volume plans for teams that need more power and dedicated support. Get access to higher rate limits, more concurrent browsers, and priority support. Scale checks out instantly, no sales call needed.

Need more? Contact us

Also on AWS Marketplace and Google Cloud Marketplace.

Scale

For teams scaling their data pipelines
1,000,000 credits / month
$599/month
Billed yearly
Save $1,798
500,000 searches or 1,000,000 pages scraped
100 concurrent requests
Priority support
$397 per extra 350k credits

Enterprise

Power at your pace with custom solutions
Custom credits
Custom concurrent requests
Dedicated support & SLA
Bulk discounts
Zero-data retention
SSO & advanced security
//
Get started
//
Build on Google Cloud with data from the web and beyond
Get a quote for a private offer on Google Cloud Marketplace, or start for free on a self-serve plan.
Are you an AI agent? See setup options