How to Use the Netdata MCP in Google ADK

Q: How do I restrict which MCP tools the agent can use?

Pass a list of strings to the toolnames parameter when creating your toolset. This keeps your agent focused entirely on listcharts instead of wandering into topology commands.

Feed massive Netdata infrastructure metrics into Google ADK for long-context Gemini analysis.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Netdata MCP to Google ADK

Create your Vinkius account to connect Netdata 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 Netdata with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-Context Metric Analysis

The Netdata MCP server pipes high-resolution node metrics straight into Google ADK. Gemini's massive context window can ingest thousands of data points from `get_all_metrics` without losing track of the timeline. You initialize this connection using McpToolset with HTTP transport. The agent correlates live CPU spikes against historical patterns stored in BigQuery, giving you root-cause analysis based on actual system behavior.

Netdata MCP Server Alerting

Massive clusters generate too much noise for human operators. Your Gemini agent filters this chaos by calling `list_space_alerts` and cross-referencing the output with your Vertex AI incident models. Restricting exposed tools is simple with the tool_names filter. You can limit a specific agent to just `get_alarms` and `get_chart_data`, preventing it from wasting tokens on topology discovery.

Dynamic Cloud Topology Mapping

Enterprise environments shift constantly as containers spin up and down. The MCP agent tracks these changes by iterating through `list_spaces`, `list_rooms`, and `list_space_nodes`. It builds a live graph of your infrastructure in memory. When a node fails, the agent uses `get_agent_info` to check its last known state before triggering your Google Cloud alerting pipeline.

Setup guide

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

Install the SDK and configure StreamableHttpServerParameters with your Vinkius URL. Wrap that in an McpToolset and pass it to your LlmAgent tools array.

Yes, the massive token window easily handles bulk telemetry. Your agent can read the entire output of `get_all_metrics` and identify anomalies across hundreds of charts simultaneously.

Pass a list of strings to the tool_names parameter when creating your toolset. This keeps your agent focused entirely on `list_charts` instead of wandering into topology commands.

The agent handles this natively. It fetches live states via `get_alarms` and immediately writes or compares that data against your existing BigQuery incident tables.

This integration accesses hardware utilization rates, network throughput, and alert configurations. Vinkius secures the transport layer with zero-trust authentication, ensuring your Gemini models only process this sensitive node data via single-use endpoint tokens.

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