How to Use the Northflank (Developer Cloud & Orchestration) MCP in Pydantic AI

Q: How do I restart services safely?

The agent calls restartservice to cycle your container replicas. Because the input parameters are validated against Pydantic models, you cannot pass invalid service IDs or project names.

Manage your Northflank environments with type-safe runtime validation using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Northflank (Developer Cloud & Orchestration) MCP to Pydantic AI

Create your Vinkius account to connect Northflank (Developer Cloud & Orchestration) 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 Northflank (Developer Cloud & Orchestration) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe project provisioning via Pydantic AI

The `create_project` tool provisions a new cloud region and configures ingress routing using the MCP Server. Using Pydantic AI, the returned project metadata is validated against strict Python type schemas at runtime. If the API response deviates from the expected structure, the framework raises a validation error immediately. This prevents your deployment scripts from executing further steps with corrupt or missing project IDs.

Validate container configurations and builds

The `get_service` tool retrieves structural details about your microservices, including scaling limits and SSL configurations. Your agent validates this data against your local Pydantic models to ensure compliance with production standards. When you trigger deployments using `trigger_build`, the agent monitors the build status. It ensures that the resulting container configuration matches your strict schema before allowing traffic to hit the new pods.

Safe secret injection and auditing

The `list_secrets` tool fetches environment variables and database URLs from your VPC via the MCP integration. Your type-safe agent parses these secrets into structured models, verifying that required fields like port numbers are actual integers. If a database connection string is malformed, the agent halts the pipeline before calling `restart_service`. This strict validation prevents application crashes caused by bad configuration data.

Setup guide

Set up Northflank (Developer Cloud & Orchestration) 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": {
        "northflank-developer-cloud-orchestration-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Northflank (Developer Cloud & Orchestration) 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 Northflank. 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 Northflank (Developer Cloud & Orchestration) 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 Northflank (Developer Cloud & Orchestration) MCP in Pydantic AI

Use the MCPToolset class pointing to your Vinkius HTTP endpoint. Pass this toolset instance directly into your Agent's toolsets parameter to enable type-safe tool execution.

Pydantic AI will raise a validation error at runtime if the response fields do not match your schemas. This prevents silent execution failures and ensures your deployment pipeline is completely predictable.

Yes, the framework is model-agnostic. You can run local models or commercial APIs; the server will still validate all inputs and outputs for tools like `list_services` and `list_jobs`.

The agent calls `restart_service` to cycle your container replicas. Because the input parameters are validated against Pydantic models, you cannot pass invalid service IDs or project names.

The MCP Server processes project IDs, service configurations, and environment variables. All operations run inside secure, ephemeral V8 isolates, ensuring your secrets are never cached, stored, or exposed to third parties.

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