How to Use the Gridscale (IaaS & PaaS Cloud Hosting API) MCP in Google ADK

Q: How does the agent handle storage volumes that are currently unattached?

The agent can call liststorages to find all volumes in your account. By comparing this list with active server attachments, it can identify orphaned disks and suggest linking them via linkstoragetoserver or deleting them to save costs.

Manage your Gridscale cloud infrastructure directly from Google ADK using Gemini's long-context reasoning with this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gridscale (IaaS & PaaS Cloud Hosting API) MCP to Google ADK

Create your Vinkius account to connect Gridscale (IaaS & PaaS Cloud Hosting API) 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 Gridscale (IaaS & PaaS Cloud Hosting API) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise audits using Google ADK and MCP

Gemini's massive context window lets your Google ADK agent analyze your entire Gridscale footprint at once. By running `list_servers`, `list_storages`, and `list_networks`, the agent gathers data on all active assets. It can then correlate this data against your BigQuery spending logs to find idle resources that are costing you money. The agent can easily cross-reference these lists with `list_locations` to map out your multi-region deployment. This gives you a clear picture of your cloud footprint without manual spreadsheet tracking.

Location-aware cloud resource deployment

Deploying resources in the right datacenter is critical for compliance and latency. Your agent can call `list_locations` to find the closest region, then select the right operating system template using `list_templates`. Once the parameters are set, it boots the instance using `create_server`. After the instance is up, the agent can assign an IP address via `link_ip_to_server` and set up network firewalls using `list_firewalls`. This complete deployment pipeline runs autonomously based on simple natural language instructions from your team.

Automated infrastructure power management

Save on cloud costs by shutting down development environments outside of working hours. Your agent checks the status of your fleet using `get_server_power`. If a machine is running when it should not be, the agent issues an ACPI shutdown using `shutdown_server` to safely close active processes. For systems that do not respond to ACPI signals, the agent can fall back to `set_server_power` to force a shutdown. This programmatic control helps keep your resource usage optimized without manual intervention.

Setup guide

Set up Gridscale (IaaS & PaaS Cloud Hosting API) 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 Gridscale (IaaS & PaaS Cloud Hosting API) 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="Gridscale (IaaS & PaaS Cloud Hosting API)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Gridscale (IaaS & PaaS Cloud Hosting API) 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 Gridscale. 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 Gridscale (IaaS & PaaS Cloud Hosting API) 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 Gridscale (IaaS & PaaS Cloud Hosting API) MCP in Google ADK

You initialize the tools using the McpToolset class with your HTTP endpoint URL. Pass this toolset into the tools parameter of your LlmAgent, and Gemini will automatically understand when to call tools like `list_servers` to inspect your cloud setup.

Yes, you can. Have your agent fetch real-time performance data using `get_server_metrics`, feed it into your Vertex AI pipelines, or store it in BigQuery for long-term trend analysis and predictive scaling.

Absolutely. When defining the McpToolset, you can use the tool_names filter to expose only safe listing tools like `list_servers` and `list_networks`, preventing the agent from executing destructive commands like `shutdown_server`.

The agent can call `list_storages` to find all volumes in your account. By comparing this list with active server attachments, it can identify orphaned disks and suggest linking them via `link_storage_to_server` or deleting them to save costs.

Your API credentials are encrypted and stored in the secure Vinkius vault. When your agent calls tools like `list_firewalls`, the server injects the credentials inside an isolated sandbox, ensuring your private cloud access keys are never exposed to the LLM.

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