How to Use the CoreWeave (AI GPU Cloud) MCP in Google ADK

Q: Can I use Gemini to analyze CoreWeave (AI GPU Cloud) logs via Google ADK?

Yes, your agent calls querylogs to retrieve diagnostic data. Gemini's large context window allows it to parse thousands of lines of Loki logs at once to pinpoint GPU scheduling failures.

Q: How does this integration handle the privacy of my CoreWeave VPC configurations?

All network topology details fetched via listvpcs are processed in memory and never stored. Vinkius isolates the execution environment to ensure your private network configurations remain secure.

Connect your Google ADK agents to CoreWeave GPU clusters and scale inference models inside Gemini long-context workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CoreWeave (AI GPU Cloud) MCP to Google ADK

Create your Vinkius account to connect CoreWeave (AI GPU Cloud) 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 CoreWeave (AI GPU Cloud) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map BigQuery Data to CoreWeave MCP Server Deployments

This MCP Server connects your Google ADK agent to CoreWeave's deployment tools like `create_deployment` and `update_deployment` to link high-performance hardware with your Google Cloud data pipelines. Your Gemini agent reads model performance data from BigQuery and immediately triggers changes to match workload demands. No manual scripting is required. The agent evaluates historical telemetry alongside real-time cluster status to make intelligent provisioning decisions.

Feed Raw Prometheus Metrics to Gemini Long Context

The `query_metrics` and `query_logs` tools feed raw infrastructure metrics directly into Gemini's massive context window. Your agent analyzes hours of Loki logs and system performance data in a single pass to find bottlenecks. This gives the model the complete picture of your GPU workloads. It solves complex system issues that shorter-context models miss entirely.

Direct VPC Configuration via Google ADK Agents

Your enterprise agents use `create_vpc` and `create_gateway` to set up isolated networking environments on CoreWeave. You configure these resources dynamically without leaving your Google Cloud management workflows. The agent verifies the network setup using `get_vpc` before launching any compute nodes. This guarantees your GPU clusters always deploy into a secure, pre-configured network.

Setup guide

Set up CoreWeave (AI GPU Cloud) 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 CoreWeave (AI GPU Cloud) 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="CoreWeave (AI GPU Cloud)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to CoreWeave (AI GPU Cloud) 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 CoreWeave. 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 CoreWeave (AI GPU Cloud) 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 CoreWeave (AI GPU Cloud) MCP in Google ADK

The Google ADK maps the MCP tools into a standard toolset object. Your Gemini model selects specific operations like `list_clusters` or `create_capacity_claim` based on your conversational prompts.

Yes, your agent calls `query_logs` to retrieve diagnostic data. Gemini's large context window allows it to parse thousands of lines of Loki logs at once to pinpoint GPU scheduling failures.

Vinkius manages the authentication layer, so your Gemini agents never handle raw CoreWeave API keys. The SDK communicates with our secure gateway using a single, encrypted token.

We recommend the Streamable HTTP transport when using this MCP Server on GCP. It provides a stable, low-latency connection from your serverless functions to the CoreWeave API.

All network topology details fetched via `list_vpcs` are processed in memory and never stored. Vinkius isolates the execution environment to ensure your private network configurations remain secure.

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