How to Use the Firecrawl MCP in Google ADK

Q: How do I check my Firecrawl credit status in Google ADK?

Call getapiusage. It returns your current balance, which you can use to set thresholds inside your agent's control logic.

Q: Does Firecrawl integrate with Google ADK for site mapping?

Yes. The mapwebsitestructure tool returns a JSON list of URLs, letting your agent parse the site hierarchy before it scrapes individual pages.

Q: Can I cancel a Firecrawl job from Google ADK?

Yes, use the cancelactivecrawl tool. Provide the job ID, and the server stops the process instantly.

Turn web data into structured context for your Google ADK enterprise agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Firecrawl MCP to Google ADK

Create your Vinkius account to connect Firecrawl to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Firecrawl with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ingest web data for Google ADK

The `scrape_url` tool converts live web pages into markdown optimized for Gemini's long-context window. Your agent pulls only the necessary text, keeping your token usage efficient. This integration allows your agent to process information from external sites alongside your BigQuery data. You get a unified view of internal and external sources without building custom parsers.

Automate site discovery for Google ADK

Use `map_website_structure` to identify all reachable endpoints on a domain. This helps your agent decide which pages to target for deeper extraction. Once mapped, `start_crawl` initiates the heavy lifting. You can track the status of these background jobs via `get_crawl_status` to ensure your data pipeline remains up to date.

Control crawl budgets for Google ADK

The `get_api_usage` tool provides real-time feedback on your credit consumption. This is vital when your agent manages large-scale data gathering tasks. If a specific crawl exceeds expected parameters, use `cancel_active_crawl` to halt execution. This prevents runaway API costs from impacting your Google Cloud infrastructure budget.

Setup guide

Set up Firecrawl MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Firecrawl tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Firecrawl_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Firecrawl tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Firecrawl. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Firecrawl now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Firecrawl MCP in Google ADK

Call `get_api_usage`. It returns your current balance, which you can use to set thresholds inside your agent's control logic.

Yes. The `map_website_structure` tool returns a JSON list of URLs, letting your agent parse the site hierarchy before it scrapes individual pages.

Yes, use the `cancel_active_crawl` tool. Provide the job ID, and the server stops the process instantly.

All traffic is handled via encrypted MCP endpoints. No raw HTML is persisted on our end; we only return the markdown output.

It is. Since it returns clean markdown, you can feed large amounts of scraped text directly into your Gemini-powered agent's long-context window.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript

Mastra AI sdk-typescript

Start using the Firecrawl MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started