How to Use the Fireblocks MCP in Google ADK

Q: How do I register custom ERC-20 tokens for my enterprise vaults?

Your agent executes registerasset with the contract address and blockchain details, then runs createvaultaccountasset to deploy the wallet.

Connect your enterprise Google ADK agents directly to the Fireblocks MCP Server to automate digital asset treasury operations with BigQuery data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fireblocks MCP to Google ADK

Create your Vinkius account to connect Fireblocks 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 Fireblocks with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

BigQuery-Driven Vault Management

Accessing your vault balances starts with `list_vault_accounts` which your Google ADK agent runs to sync on-chain balances with your BigQuery ledger. The agent analyzes historical transaction patterns in your Google Cloud environment, then uses `create_vault_account` to spin up new wallets as liquidity demands change. Because Gemini handles massive context windows, your agent evaluates months of financial data to optimize your vault layout. You pass the toolset directly to your LlmAgent in python. The agent automatically runs `get_vault_account_asset` to check specific token balances and matches them against your enterprise reporting databases in real time.

Automated Gas Station Management via Google ADK

Monitoring gas thresholds requires `get_gas_station` which your Google ADK agent calls to inspect your current fueling settings. When network fees spike, the agent reads historical gas metrics from Vertex AI and executes `update_gas_station` to adjust your auto-fueling limits. This keeps your enterprise transactions moving without manual dev ops intervention. The Gemini-powered agent uses `estimate_network_fee` to calculate optimal gas limits before updating your configuration. This direct integration ensures your automated gas station never runs dry during high-volume trading periods.

Enterprise Compliance with Google ADK MCP Server

Executing compliance checks requires `validate_travel_rule` which your Google ADK agent calls whenever an external transfer is requested. The agent cross-references the destination address against your BigQuery database of verified counterparties and runs `list_vasps` to check regulatory status. This prevents your enterprise from sending digital assets to unsanctioned entities. If the destination is unknown, the agent runs `get_screening_transaction` to analyze the risk score before committing funds. You maintain a clean audit trail directly within your Google Cloud logging infrastructure.

Setup guide

Set up Fireblocks 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 Fireblocks 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="Fireblocks_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Fireblocks 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 Fireblocks. 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 Fireblocks 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 Fireblocks MCP in Google ADK

Your Google ADK agent reads records from BigQuery, processes the data using Gemini, and then passes the validated parameters directly to Fireblocks tools via MCP.

Yes, Gemini's million-token context window easily processes large arrays from `list_transactions` and `list_webhook_notifications` to reconcile your corporate ledger without truncation.

The server runs in a secure V8 sandbox managed by Vinkius, communicating via HTTP with your Google ADK python application. No API keys or transaction payloads are exposed to outside networks.

Your agent executes `register_asset` with the contract address and blockchain details, then runs `create_vault_account_asset` to deploy the wallet.

Your Fireblocks API credentials and private vault configurations are encrypted in transit and processed within isolated, zero-trust memory spaces. Vinkius never caches your private keys or transaction payloads, ensuring compliance with strict enterprise data boundaries.

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