How to Use the Netdata MCP in Mastra AI

Q: How do I connect the Netdata MCP Server to a Mastra AI agent workflow?

Instantiate the client using new MCPClient with the Netdata server URL. Then, call listTools() and spread them directly into your agent's tool array to let it execute commands like getalarms.

Q: Can a Mastra AI workflow automatically resolve Netdata alerts?

The MCP Server provides read-only diagnostics like listspacealerts and getchartdata. Your workflow must use these tools to detect issues, then branch to a separate system-level tool to execute the actual fix.

Q: Do I need to configure human-in-the-loop approval for telemetry checks?

Since tools like getallmetrics only retrieve performance data, you can run them fully autonomously. You only need requireToolApproval if your workflow triggers destructive system actions based on that data.

Build self-healing infrastructure workflows using Mastra AI and the Netdata 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 Netdata MCP to Mastra AI

Create your Vinkius account to connect Netdata to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Auto-Retry Performance Audits with Mastra AI

When a server acts up, you want immediate answers, not a broken script. Mastra AI uses the Netdata MCP Server to run `get_all_metrics` and automatically retries the call with exponential backoff if the network hiccups. If a node fails to respond, the workflow engine branches instantly. The agent checks `list_space_nodes` to find healthy alternatives and continues gathering telemetry without crashing your pipeline.

Conditional Alert Routing

Stop blasting Slack with every minor warning. By using `list_space_alerts` within a Mastra workflow, your agent can evaluate the severity of active alarms before taking action. If the alert is critical, the agent triggers a high-priority incident response path. For minor warnings, it simply logs the event and schedules a follow-up check using `get_agent_info` to see if the issue resolved itself.

Automated Node Discovery and Verification

Scaling up your cluster shouldn't require manual configuration updates. The agent uses `list_spaces` and `list_rooms` to discover new infrastructure footprints as they spin up. Once discovered, the agent verifies each node's health by running `list_room_nodes`. This lets your workflows dynamically register new targets for telemetry collection without human intervention.

Setup guide

Set up Netdata MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Netdata tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "netdata-mcp-client",
  servers: {
    "netdata-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Netdata Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Netdata tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Netdata transactions"
);
console.log(result.text);

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 Mastra AI

Instantiate the client using `new MCPClient` with the Netdata server URL. Then, call `listTools()` and spread them directly into your agent's tool array to let it execute commands like `get_alarms`.

The MCP Server provides read-only diagnostics like `list_space_alerts` and `get_chart_data`. Your workflow must use these tools to detect issues, then branch to a separate system-level tool to execute the actual fix.

Mastra AI has built-in retry mechanisms that manage transient network issues. However, you should design your workflows to cache results from `list_charts` instead of querying the node repeatedly.

Since tools like `get_all_metrics` only retrieve performance data, you can run them fully autonomously. You only need `requireToolApproval` if your workflow triggers destructive system actions based on that data.

The server only accesses system performance metrics, active alarm configurations, and node lists. Your raw database contents and sensitive application files remain completely untouched and isolated within your private network.

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