How to Use the Marqeta MCP in Google ADK

Q: How do I configure the Marqeta MCP Server in Google ADK?

Initialize a McpToolset using StreamableHttpServerParameters with your Vinkius URL. Pass this toolset to your LlmAgent initialization.

Q: Can a Google ADK agent simulate Marqeta transactions?

It can. The agent uses simulateauthorization and simulateclearing to mock payment flows. This is useful when testing new Vertex AI fraud models against simulated swipe data.

Q: How do I restrict which Marqeta MCP tools the Google ADK agent sees?

Use the toolnames filter when setting up the McpToolset. If you only want the agent checking balances, restrict it to getbalances and listcardsbyuser.

Q: Can Marqeta and Google ADK handle business onboarding?

You can script the entire flow. The agent calls createbusiness, runs performkyc, and then uses createcardproduct to spin up a new corporate expense program.

Give your Google ADK agents direct access to Marqeta to issue cards, clear transactions, and sync payment data with BigQuery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Marqeta MCP to Google ADK

Create your Vinkius account to connect Marqeta 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 Marqeta with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Google ADK MCP Server Integration

You have massive amounts of user data in BigQuery, and you want to issue cards based on that data. By connecting this MCP Server, your Gemini agent can read a user profile, trigger `create_user`, and execute `perform_kyc` in one continuous pipeline. Gemini's massive context window means you can feed it thousands of transaction logs alongside the Marqeta toolset. The agent can analyze the history and decide whether to call `create_velocity_control` to restrict a specific merchant category.

Automate Account Funding

Managing Just-in-Time funding requires fast, predictable API calls. Your Google ADK agent can monitor internal triggers and immediately execute `create_gpa_order` or `create_ach_funding_source`. If a user needs a direct deposit reversed, the agent handles it via `create_direct_deposit_transition`. The agent reads the exact ledger state using `get_balances` before moving any money.

Control Card States Dynamically

Fraud detection models in Vertex AI can spot anomalies fast. When they do, your agent can instantly call `create_card_transition` to suspend the compromised card. The agent can also handle user-requested changes. If an employee forgets their PIN, the agent triggers `create_pin_control_token` and `update_pin` without needing a human in the loop.

Setup guide

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

Initialize a `McpToolset` using `StreamableHttpServerParameters` with your Vinkius URL. Pass this toolset to your `LlmAgent` initialization.

It can. The agent uses `simulate_authorization` and `simulate_clearing` to mock payment flows. This is useful when testing new Vertex AI fraud models against simulated swipe data.

Use the `tool_names` filter when setting up the `McpToolset`. If you only want the agent checking balances, restrict it to `get_balances` and `list_cards_by_user`.

You can script the entire flow. The agent calls `create_business`, runs `perform_kyc`, and then uses `create_card_product` to spin up a new corporate expense program.

The server processes strict financial records like direct deposit routing details and PIN control tokens. Vinkius runs the server in an ephemeral V8 isolate, ensuring that Gemini only accesses the specific transaction data required for the current prompt, with zero persistent storage.

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