How to Use the Netdata MCP in LangChain

Q: How do I connect LangChain to the Netdata MCP server?

Install langchain-mcp-adapters. Initialize a MultiServerMCPClient pointing to the server endpoint, call client.gettools(), and pass the array to your ReAct agent.

Q: Can LangChain aggregate metrics from multiple Netdata spaces?

Yes. The agent loops through listspaces, extracting IDs. It then runs listspacealerts across all of them, feeding a unified status report into your chain.

Build multi-step observability pipelines. LangChain agents query Netdata metrics via this MCP Server and resolve infrastructure alerts automatically.

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 LangChain

Create your Vinkius account to connect Netdata to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build LangChain Alert Resolution Pipelines

Your ReAct agent needs context before it pages an engineer. Using the `get_alarms` tool, the agent grabs active alerts from your cluster. It then decides the next step based on the severity and node state. Instead of a human digging through dashboards, the agent pipes the alert node ID directly into `list_charts`. It chains that output to `get_chart_data`, pulling the exact CPU or memory spike that triggered the alarm. You get the root cause handed to you in Slack.

Trace Netdata MCP Server API Calls

Observability requires knowing exactly what your automation is doing. LangSmith tracks every invocation of `list_spaces` and `list_rooms`. You see the exact latency for each API request your agent makes to the monitoring backend. If a script hammers the Netdata Cloud with `get_all_metrics` requests, you catch it immediately. The token usage and input parameters for every tool call sit right in your trace logs. You optimize the pipeline before rate limits kick in.

Map Cloud Infrastructure Topologies

Hardcoding node IDs breaks the minute you scale. Your LangChain agent dynamically discovers your environment using `list_space_nodes` and `list_room_nodes` to build an accurate mental model of your cluster. The output feeds directly into your configuration management chains. When a new database server spins up, the agent detects it via `get_agent_info` and automatically updates your internal registry. Zero manual intervention required.

Setup guide

Set up Netdata MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Netdata tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "netdata-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Netdata transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install `langchain-mcp-adapters`. Initialize a `MultiServerMCPClient` pointing to the server endpoint, call `client.get_tools()`, and pass the array to your ReAct agent.

Yes. The agent loops through `list_spaces`, extracting IDs. It then runs `list_space_alerts` across all of them, feeding a unified status report into your chain.

Scripts break when APIs change or outputs vary. A ReAct agent dynamically decides which tool to call next based on the actual metric data it gets back from `get_chart_data`.

It logs everything. If your agent gets stuck in a loop calling `get_all_metrics`, the trace shows the exact input and output payloads. You debug the logic flaw instantly.

Vinkius runs this MCP integration in an ephemeral V8 isolate. The tools only read node metrics and alert states. Your agent token is passed securely, and the sandbox destroys itself after the chain finishes executing.

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