How to Use the NetBird MCP in OpenAI Agents SDK

Q: How do I connect the NetBird MCP Server to the OpenAI Agents SDK?

Install the SDK via pip and initialize the server using MCPServerStreamableHttp. Pass this instance into your Agent constructor's mcpservers list to let your agents discover the networking tools.

Q: Can the OpenAI Agents SDK handle temporary NetBird peer access?

Yes, your agent can call createtemporaryaccesspeer to grant short-term network access. The SDK's built-in guardrails can restrict this action to specific time windows or approved user groups.

Secure your network infrastructure by letting your OpenAI Agents SDK automatically provision NetBird zero-trust policies and peers.

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 OpenAI Agents SDK

Create your Vinkius account to connect NetBird to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Zero-Trust Policies with OpenAI Agents SDK

Managing NetBird security boundaries manually inside your OpenAI Agents SDK workflow gets messy fast. Your agent can run `create_policy` and `create_posture_check` via this MCP Server to instantly restrict network access based on real-time device posture or location. OpenAI's native guardrails ensure your agent doesn't accidentally wipe out your entire NetBird routing table. Before the agent executes `delete_policy`, the SDK validates the action against your safety constraints, keeping your production NetBird environments safe from runaway automation loops.

Manage Multi-Agent NetBird Onboarding

NetBird setup keys shouldn't live forever in plaintext inside your OpenAI Agents SDK environment. This MCP Server lets your specialized onboarding agent generate single-use credentials on demand using `create_setup_key` and assign them to specific groups with `create_group`. Once the task completes, your OpenAI agent hands off the NetBird session to a monitoring agent. The transition between these OpenAI agents happens under a single tracing context that monitors NetBird state. You can watch the handoff on your OpenAI dashboard, tracking exactly when the onboarding agent finished creating the NetBird peer and when the auditing agent started verifying the connection.

Track Network Activity Directly in OpenAI Logs

Compliance requires a clear trail of who changed what inside your NetBird configuration during an OpenAI agent run. Your agent monitors active NetBird sessions using `list_audit_events` and `list_network_traffic_events` to flag anomalous connections. If an unauthorized peer tries to connect, your OpenAI agent immediately triggers `update_user` to block the NetBird account. Every API call made by this MCP Server streams directly through your OpenAI telemetry. This gives your security team a unified view of OpenAI agent decisions and NetBird network status without jumping between separate logging pipelines.

Setup guide

Set up NetBird MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all NetBird tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives NetBird tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate NetBird tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="NetBird Agent",
            instructions="You have access to NetBird tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the SDK via pip and initialize the server using `MCPServerStreamableHttp`. Pass this instance into your Agent constructor's `mcp_servers` list to let your agents discover the networking tools.

Yes, your agent can call `create_temporary_access_peer` to grant short-term network access. The SDK's built-in guardrails can restrict this action to specific time windows or approved user groups.

You define strict validation rules inside your agent definition before exposing tools like `delete_network`. This ensures the model cannot execute destructive commands unless specific pre-conditions are met.

The SDK catches the API error and passes the raw failure details back to the agent. This allows your agent to retry the action or route the issue to a human administrator.

This server only processes NetBird setup keys, peer IP addresses, and routing tables inside an ephemeral sandbox. Your sensitive network configurations never persist on the host, keeping your topology metadata secure.

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