How to Use the NetBird MCP in LangChain

Q: How do I get started with the NetBird MCP Server and LangChain?

First, install the langchain-mcp-adapters package. Then, instantiate the MultiServerMCPClient with your Vinkius endpoint URL and token. Call client.gettools() and pass the resulting list directly to your LangChain agent.

Q: How can my agent handle temporary access for contractors in NetBird using LangChain?

Your agent can call createtemporaryaccesspeer to generate short-lived access for a specific device. You can chain this with a createpolicy call that limits the temporary peer to only the resources they absolutely need.

Build autonomous network management chains for your NetBird environment using LangChain's composable tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NetBird MCP to LangChain

Create your Vinkius account to connect NetBird 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 NetBird with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate User Onboarding from Invite to Access

This MCP Server gives your LangChain agent the tools to run a complete user onboarding sequence. A chain can start by calling `create_user_invite` to generate a link for a new hire. The agent then waits and polls `list_user_invites` until the user has accepted. Once the user is active, their ID is passed to the next link in the chain, which calls `update_user` to assign them to the correct access groups. The entire flow, from invitation to active peer, is a single, traceable agent execution you can monitor in LangSmith.

Manage NetBird Policies as Code with this MCP Server

Stop managing access rules by hand. Build an agent that reads policy definitions from a Git repository. For a new policy, the agent first calls `list_groups` and `list_network_resources` to fetch the live IDs for your destinations and sources. It then uses those IDs to construct and run a `create_policy` call, creating the rule in NetBird. If a policy already exists, the agent can use `update_policy` instead. This turns your network access control into a fully automated CI/CD pipeline.

Chain Security Audits and Remediation Steps

Create a security agent that runs on a schedule. Its first step is to call `list_audit_events` to get the latest activity logs. That data is then passed to another LLM in the chain, which is prompted to find suspicious activity, like a user being removed unexpectedly. If the agent finds an anomaly, it triggers a remediation chain. It could use `update_user` to immediately block a suspicious account, revoke a key with `update_setup_key`, or simply send a notification with the relevant event data. It's a closed-loop system for monitoring and response.

Setup guide

Set up NetBird 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 NetBird 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({
    "netbird-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 NetBird 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 NetBird. 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 NetBird 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 NetBird MCP in LangChain

First, install the `langchain-mcp-adapters` package. Then, instantiate the `MultiServerMCPClient` with your Vinkius endpoint URL and token. Call `client.get_tools()` and pass the resulting list directly to your LangChain agent.

Yes. The client supports multi-server aggregation. You can configure it with multiple Vinkius endpoint tokens, and the agent will get a unified list of tools that can target different NetBird accounts.

A great starting point is an onboarding chain. Build an agent that takes an email address, calls `create_user_invite`, then uses `update_user` to add that new user to a default group. It's a simple sequence that shows the power of chaining tool calls.

Your agent can call `create_temporary_access_peer` to generate short-lived access for a specific device. You can chain this with a `create_policy` call that limits the temporary peer to only the resources they absolutely need.

This server processes your NetBird account details, user information, peer lists, and policy configurations. Every tool call from your agent runs in a V8 Isolate sandbox on Vinkius, which is destroyed after the request finishes. Your NetBird token is encrypted at rest and only used for outbound API calls.

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