How to Use the NetBird MCP in Pydantic AI

Q: How do I add the NetBird MCP Server to a Pydantic AI agent?

Initialize the connection using MCPToolset with the server's HTTP URL. Pass the toolset directly into your Agent's toolsets parameter to enable type-safe networking tools.

Q: Can Pydantic AI safely manage NetBird setup keys?

Yes, your agent can call createsetupkey while enforcing strict validation on key expiration and auto-assigned groups. This guarantees that every generated key conforms to your security schemas.

Build bulletproof network automation using Pydantic AI to validate every NetBird configuration at runtime.

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 Pydantic AI

Create your Vinkius account to connect NetBird to Pydantic 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 NetBird with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe NetBird Policy Generation with Pydantic AI

Hallucinated NetBird network policies can break your entire firewall during Pydantic AI agent runs. This MCP Server forces your Pydantic AI agent to pass all parameters through strict type checks before calling `create_policy` or `update_policy`. If the model tries to pass an invalid port range or malformed IP, Pydantic AI rejects the NetBird API call instantly. You don't have to worry about silent NetBird routing failures down the line. The Pydantic AI framework validates the API response against strict schemas, ensuring that fields returned by `get_policy` match your NetBird application's expected data models exactly.

Secure Peer Provisioning with Strict Schemas

Automated NetBird peer onboarding requires absolute precision within Pydantic AI. Your Pydantic AI agent generates temporary access credentials using `create_temporary_access_peer` and configures DNS configurations via `create_nameserver`. Every generated NetBird peer object is validated at runtime to ensure it contains required cryptographic and network properties. If a NetBird API update changes the response payload, your Pydantic AI agent fails loudly. This prevents your Pydantic AI code from processing incomplete NetBird peer data or setting up misconfigured routes.

Audit Network Topology with Zero Hallucinations

Inspecting active NetBird peers requires reliable data structures in Pydantic AI. This MCP Server lets your Pydantic AI agent call `list_peers` and `list_groups` to map your current zero-trust topology. Pydantic AI parses these lists into typed models, making it impossible for the agent to hallucinate active NetBird connections or group memberships. This type-safe mapping allows you to write deterministic assertions around your NetBird network security. You can run automated NetBird audits using `list_audit_events` and know that every event payload is structurally sound before parsing with Pydantic AI.

Setup guide

Set up NetBird MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "netbird-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to NetBird tools.",
)

result = await agent.run("List recent NetBird transactions")
print(result.output)

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 Pydantic AI

Initialize the connection using `MCPToolset` with the server's HTTP URL. Pass the toolset directly into your Agent's `toolsets` parameter to enable type-safe networking tools.

The framework validates all agent inputs against Pydantic models before executing `create_policy`. If the agent generates an invalid protocol or port, the run fails immediately with a validation error.

Yes, your agent can call `create_setup_key` while enforcing strict validation on key expiration and auto-assigned groups. This guarantees that every generated key conforms to your security schemas.

Pydantic AI raises a validation error at runtime instead of letting the agent proceed with corrupted data. This protects your downstream automation scripts from unexpected API changes.

The server processes sensitive NetBird network data, including peer tokens, routing tables, and posture rules, entirely in memory within a zero-trust sandbox. No configuration data is cached or stored outside your execution environment.

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