How to Use the Argo CD (GitOps) MCP in Google ADK

Q: Can I limit the agent to only read cluster data?

You can. Pass a specific list to the toolnames filter when setting up the toolset. This prevents the model from accidentally triggering a rollback.

Give your Gemini models direct control over Kubernetes deployments. Connect Argo CD (GitOps) to Google ADK in minutes.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Argo CD (GitOps) MCP to Google ADK

Create your Vinkius account to connect Argo CD (GitOps) 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 Argo CD (GitOps) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze logs with this MCP Server

Gemini's massive context window changes how you debug crashed pods. Your agent pulls huge text dumps using `get_application_logs` and feeds them straight into the model. Instead of searching through terminal outputs manually, you ask Gemini to find the exact stack trace causing the crash loop. It reads the whole history and pinpoints the bad commit.

Manage multi-cluster rollouts

Enterprise infrastructure sprawls across dozens of environments. Your agent can map out the entire fleet by calling `list_clusters` and `list_applications` to build a real-time topology map. When a security patch drops, the agent orchestrates the update. It triggers `sync_application` across dev, staging, and prod in sequence while verifying health checks at each step.

Automate project scaffolding

Onboarding new engineering teams requires annoying boilerplate setup. A Google ADK agent handles the grunt work by executing `create_project` and `add_repository` as soon as a request is approved. You can restrict which tools the agent accesses. Use the tool_names filter in your Python code to expose only the read-only commands if you want a strict auditing agent.

Setup guide

Set up Argo CD (GitOps) 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 Argo CD (GitOps) 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="Argo CD (GitOps)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Argo CD (GitOps) 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 Argo CD. 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 Argo CD (GitOps) 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 Argo CD (GitOps) MCP in Google ADK

Install google-adk and initialize an McpToolset using StreamableHttpServerParameters. Pass that toolset directly to your LlmAgent instance.

Absolutely. Gemini's long context window is perfect for this task. It ingests the full output from get_application_logs to explain exactly why a pod crashed.

Yes. The framework supports both Stdio and HTTP transports. For Vinkius hosted instances, you will use the Streamable HTTP connection.

You can. Pass a specific list to the tool_names filter when setting up the toolset. This prevents the model from accidentally triggering a rollback.

Every MCP request executes inside an isolated V8 sandbox. Vinkius never stores your GitOps repository URLs, cluster IPs, or application states at rest. The environment is entirely ephemeral.

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