How to Use the Alpic MCP in Google ADK

Q: How do I configure Alpic MCP Server within my Google ADK agent?

Initialize McpToolset with your Alpic HTTP endpoint. Pass this toolset into your Google ADK LlmAgent tools array to expose the infrastructure management capabilities. You can restrict tools using the toolnames filter.

Q: Can Google ADK run local testing with Alpic?

Yes, your Google ADK agent requests a connection token via gettunnelticket to route traffic to your local machine. This lets you test your custom Alpic tools with Gemini before deploying them to Google Cloud.

Q: How does Alpic integrate with Google ADK team workflows?

Your Google ADK agent uses listteams to identify your active organization workspace. It then calls createproject to build isolated Alpic environments for different development teams automatically.

Q: How do I publish Alpic tools to the MCP registry using Google ADK?

Your Google ADK agent executes publishtoregistry to share your custom tools publicly. This registers your Alpic server with the official directory once your builds pass health checks.

Connect Alpic to your Google ADK pipelines to manage your MCP Server infrastructure via Gemini long-context reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Alpic MCP to Google ADK

Create your Vinkius account to connect Alpic 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 Alpic with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy Alpic MCP Server tools from Google ADK runtimes

`deploy_environment` triggers asynchronous deployments of your custom Alpic toolsets directly from your Gemini agent. The Google ADK agent monitors the build status using `get_deployment` to ensure your new tools are live. This mechanism allows your Google ADK agent to scale up backend infrastructure when your BigQuery workloads spike. You control the entire Alpic lifecycle without leaving your Python runtime.

Manage Alpic variables inside Google ADK

`add_variable` configures environment variables for your deployed Alpic MCP servers dynamically. Your Gemini agent updates database URLs or Vertex AI keys using this tool during Google ADK runtime execution. The agent uses `list_variables` to verify existing Alpic configurations before applying updates. This ensures your Google ADK pipelines always connect to the correct endpoints.

Debug Alpic infrastructure with Gemini reasoning

`get_deployment_logs` pulls raw build and runtime logs from Alpic directly into Gemini's million-token context window. The model analyzes these logs alongside your Google ADK telemetry to diagnose startup failures. Your Google ADK agent then calls `update_project` to fix configuration errors automatically. This loop resolves Alpic deployment blocks. No manual intervention needed.

Setup guide

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

Initialize `McpToolset` with your Alpic HTTP endpoint. Pass this toolset into your Google ADK `LlmAgent` tools array to expose the infrastructure management capabilities. You can restrict tools using the `tool_names` filter.

Yes, your Google ADK agent requests a connection token via `get_tunnel_ticket` to route traffic to your local machine. This lets you test your custom Alpic tools with Gemini before deploying them to Google Cloud.

Your Google ADK agent uses `list_teams` to identify your active organization workspace. It then calls `create_project` to build isolated Alpic environments for different development teams automatically.

Your Google ADK agent executes `publish_to_registry` to share your custom tools publicly. This registers your Alpic server with the official directory once your builds pass health checks.

Alpic isolates all deployment logs and team IDs within sandboxed runtimes. Your Google ADK agent only receives encrypted references, ensuring your Vertex AI pipelines never leak raw credentials.

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