How to Use the Ninox MCP in Pydantic AI

Q: How do I initialize Ninox MCP tools in Pydantic AI?

Use the MCPToolset class with your Vinkius server URL and pass it to your Pydantic AI Agent to register Ninox tools like listdatabases and getrecord.

Q: Can Pydantic AI execute custom Ninox scripts?

Yes, executeninoxscript lets you run complex Ninox calculations and validate the returned values inside Pydantic AI.

Q: How do I fetch a single Ninox record safely with Pydantic AI?

Use the getrecord tool to retrieve specific Ninox row details, which Pydantic AI validates against your target Python model before exposing them to your agent.

Build type-safe database pipelines with Pydantic AI validating every Ninox MCP record 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 Ninox MCP to Pydantic AI

Create your Vinkius account to connect Ninox 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 Ninox with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict type-safe Ninox record creation

`create_records` inserts rows into Ninox while Pydantic AI validates the payload structure before execution. If the agent attempts to write a Ninox field with the wrong data type, Pydantic AI raises a validation error immediately. This prevents corrupt data from polluting your Ninox relational tables. You don't have to worry about silent failures or unexpected null values in your Ninox workspace when using Pydantic AI.

Runtime validation of Ninox schemas

`get_database_schema` fetches the exact field definitions of your Ninox tables to configure your Pydantic AI models. This ensures your python application's data models match your live Ninox database configuration. When the Ninox database schema changes, the Pydantic AI validation layer catches mismatches instantly. This makes your Ninox integration highly resilient compared to brittle, unvalidated API calls.

Type-safe querying via MCP Server

`list_records` retrieves rows from your Ninox database and parses them directly into Pydantic AI models. The MCP Server acts as the secure bridge, delivering structured Ninox JSON that matches your defined schemas. Your Pydantic AI agent can confidently process these Ninox records knowing the data types are guaranteed. This eliminates runtime type errors when extracting data from Ninox.

Setup guide

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

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

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

Use the `MCPToolset` class with your Vinkius server URL and pass it to your Pydantic AI `Agent` to register Ninox tools like `list_databases` and `get_record`.

The Pydantic AI framework raises a validation error at runtime, stopping the agent from processing the bad Ninox data.

Yes, `execute_ninox_script` lets you run complex Ninox calculations and validate the returned values inside Pydantic AI.

Use the `get_record` tool to retrieve specific Ninox row details, which Pydantic AI validates against your target Python model before exposing them to your agent.

All Ninox record payloads and table schemas are processed in memory within ephemeral V8 isolates before Pydantic AI validation. Vinkius does not store your relational data, keeping your business records private.

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