How to Use the NetBird MCP in AutoGen

Q: How do I give my AutoGen agents tools for managing NetBird?

Install the autogen-extmcp package. Use the mcpservertools function with your Vinkius endpoint URL to get a list of tools. Then, pass that list to your AssistantAgent constructor.

Use collaborative AutoGen agents to debate, manage, and secure your NetBird Zero Trust network.

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 AutoGen

Create your Vinkius account to connect NetBird to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let Agents Debate Network Changes Before Applying

With AutoGen, changes happen through consensus. You can create a "ProvisioningAgent" that proposes adding a new server using a reusable `create_setup_key`. A "SecurityAgent" in the same chat can challenge this, use `list_policies` to check for risks, and argue for a one-off key instead. The agents negotiate a solution. The outcome might be a compromise where the ProvisioningAgent uses `create_temporary_access_peer` after the SecurityAgent verifies device health with a `create_posture_check`. No action is taken until the agents agree, and the entire debate is logged.

Deploy an AutoGen Team to Monitor and Respond

Build an automated security operations team. One agent's sole purpose is to run `list_audit_events` in a loop. When it detects a critical event, like `delete_policy`, it posts a message to the group chat. Another agent, a "SysAdminAgent," sees the message and can validate the action. If the change was unauthorized, it has the tools to respond immediately—perhaps by blocking a user with `update_user` or regenerating an invite with `regenerate_user_invite`. This MCP Server gives your agent team the power to act.

Build a Multi-Agent Workflow for User Access

Turn user management into a conversation between specialists. A new hire request can trigger a workflow. An "HR_Agent" verifies the user's employment status. A "ManagerAgent" provides the approval. Finally, a "NetOpsAgent" joins the chat to execute the work. That NetOpsAgent uses the information from the chat to call `create_user_invite`, `update_user` to assign groups, and `list_peers` to confirm the user is connected. Every step is a recorded message, providing a clear, auditable trail for every permission change.

Setup guide

Set up NetBird MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes NetBird tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="NetBird_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent NetBird data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="NetBird_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent NetBird data")
    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 AutoGen

Install the `autogen-ext[mcp]` package. Use the `mcp_server_tools` function with your Vinkius endpoint URL to get a list of tools. Then, pass that list to your `AssistantAgent` constructor.

Yes. You can create separate MCP Server endpoints on Vinkius with different NetBird tokens, each with its own permissions. Then, provide the corresponding tools to each agent, giving your SecurityAgent read-only tools while your NetOpsAgent gets write access, for example.

A great first project is a two-agent system for access requests. One agent is the user proxy that requests access, and the other is a NetOps agent that can call `create_temporary_access_peer`. This demonstrates the conversational request-and-approve workflow that AutoGen enables.

You can have one agent responsible for gathering requirements from a user, like sources and destinations. It passes that structured data to another agent specializing in `create_policy`. This second agent validates the inputs and executes the final API call, separating planning from execution.

The server processes NetBird setup keys, posture check rules, and user account data. Each tool call from any AutoGen agent is executed in its own isolated sandbox on Vinkius. Data is not shared between these sandboxes, so one agent's call to `list_users` is invisible to another unless it's explicitly shared in the agent conversation.

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