How to Use the ncScale MCP in Pydantic AI

Q: How do I use ncScale with Pydantic AI?

You instantiate an MCPToolset with your endpoint URL and pass it to your agent. Pydantic AI then enforces validation on every response returned by the server.

Type-safe no-code observability for Pydantic AI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ncScale MCP to Pydantic AI

Create your Vinkius account to connect ncScale 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 ncScale with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe alert retrieval

Every alert pulled via `get_alert` is validated against your Pydantic models at runtime. If the API returns a malformed response, the agent stops immediately. This prevents your agent from acting on corrupted or unexpected data. It forces your system to maintain strict schema integrity during every diagnostic cycle.

Precise node status checking

Use `get_node` to fetch details about a specific integration component. Pydantic AI ensures that the returned JSON strictly matches your expected structure. This eliminates the risk of silent failures caused by API changes in your no-code tools. You get reliable data that your agent can actually use to resolve incidents.

Automated log analysis

Query your system logs with `list_logs` and let Pydantic AI validate the output. The server provides the data, and your models define the shape of the information. This pattern is ideal for production systems where correctness is non-negotiable. You’ll catch inconsistencies in your log data before they impact your monitoring logic.

Setup guide

Set up ncScale 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": {
        "ncscale-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent ncScale 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 ncScale. 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 ncScale 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 ncScale MCP in Pydantic AI

You instantiate an `MCPToolset` with your endpoint URL and pass it to your agent. Pydantic AI then enforces validation on every response returned by the server.

Yes. Every tool response is checked against your defined models. If the server returns unexpected fields, the agent will raise a validation error instead of failing silently.

Yes. The server is model-agnostic. As long as you are using the Pydantic AI framework, the type-safe validation will work regardless of which model processes the data.

The server runs externally and connects via SSE or HTTP. You simply point your `MCPToolset` to the Vinkius-managed endpoint, and the client manages the state.

The server only reads your node metadata and logs. All communication is routed through a secure, authenticated tunnel, protecting your stack configuration from exposure.

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