How to Use the MintMCP MCP in Google ADK

Q: How do I integrate MintMCP with Google ADK?

You initialize an McpToolset using the StreamableHttpServerParameters pointing to your gateway. Once configured, you pass the toolset to your LlmAgent to enable direct access to your MintMCP tools.

Q: Does MintMCP allow filtering tools for Google ADK agents?

Yes. You can use the toolnames filter when setting up your McpToolset. This ensures your agents only see the specific tools you want them to use, preventing accidental exposure of sensitive functions.

Q: How does MintMCP protect my data when using Google ADK?

The server uses mintmcpevalguardrail to intercept and validate every request. This ensures that no PII or restricted data is sent to your agents, maintaining a strict barrier between your sensitive data and the AI.

Q: How do I manage virtual server environments for Google ADK via MintMCP?

You use mintmcplistvirtualservers to see available proxies and mintmcpgetvirtualserver to verify their configuration. It gives you a clear way to isolate different agent workloads on Google Cloud.

Connect your Google ADK agents to enterprise-grade security with MintMCP for controlled access to BigQuery and cloud infrastructure.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MintMCP MCP to Google ADK

Create your Vinkius account to connect MintMCP 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 MintMCP with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Granular execution via Google ADK

Route your agent actions through a hardened gateway that doesn't sacrifice performance. The `mintmcp_run_tool_action` function proxies your commands directly to your secure integrations. This bypasses the need for messy local scripts. You get a clean interface that lets your Gemini-powered agents interact with your data safely.

Policy-driven tool access

Lock down what your agents can touch. `mintmcp_get_tool_policy` lets you define strict RBAC rules, ensuring your Google ADK agents follow your internal governance standards. It’s about limiting the blast radius. Even if an agent attempts an unauthorized operation, the gateway blocks it before the command executes.

Real-time auditing for Google Cloud agents

Get deep visibility into your agent activity by dumping logs with `mintmcp_fetch_audit_logs`. This helps you maintain a clear trail of every interaction between your agents and your cloud infrastructure. You can feed these logs into your existing monitoring stack. It turns opaque agent behavior into actionable data for your security operations.

Setup guide

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

You initialize an `McpToolset` using the `StreamableHttpServerParameters` pointing to your gateway. Once configured, you pass the toolset to your `LlmAgent` to enable direct access to your MintMCP tools.

Yes. You can use the `tool_names` filter when setting up your `McpToolset`. This ensures your agents only see the specific tools you want them to use, preventing accidental exposure of sensitive functions.

It is. Since MintMCP supports HTTP transports, your Google ADK agents can connect to the gateway from any cloud environment. You just point the client to the server URL to get started.

The server uses `mintmcp_eval_guardrail` to intercept and validate every request. This ensures that no PII or restricted data is sent to your agents, maintaining a strict barrier between your sensitive data and the AI.

You use `mintmcp_list_virtual_servers` to see available proxies and `mintmcp_get_virtual_server` to verify their configuration. It gives you a clear way to isolate different agent workloads on Google Cloud.

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