Can I check the inventory of a specific material variant?

Yes, use the `get_inventory_by_variant` tool with the unique variant ID to see current stock levels and availability in real-time.

Is it possible to list all current manufacturing orders?

Absolutely. The `list_manufacturing_orders` tool retrieves a list of all production jobs, helping you track shop floor activities.

Can I see my customer list via the agent?

Yes, the `list_customers` tool provides access to your customer database, making it easy to reference customer IDs for new sales orders.

Katana MCP Server for Pydantic AI 11 tools — connect in under 2 minutes

Name: Katana
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 11 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Katana through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Katana "
            "(11 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Katana?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Katana MCP Server

Connect your Katana Cloud Manufacturing account to any AI agent to streamline your production and shop floor operations. This MCP server enables your agent to interact with products, materials, and complex manufacturing workflows directly from natural language interfaces.

Pydantic AI validates every Katana tool response against typed schemas, catching data inconsistencies at build time. Connect 11 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Production Visibility — List and inspect manufacturing orders (MOs) and production tasks
Order Management — List, retrieve, and create sales orders (SOs) and purchase orders (POs)
Inventory Control — Get real-time stock levels for products and material variants to prevent stockouts
Catalog Exploration — Query your full product and material database, including metadata and internal IDs
Supply Chain Management — Access lists of suppliers and customers to maintain clear partner visibility

The Katana MCP Server exposes 11 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Katana to Pydantic AI via MCP

Follow these steps to integrate the Katana MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 11 tools from Katana with type-safe schemas

Why Use Pydantic AI with the Katana MCP Server

Pydantic AI provides unique advantages when paired with Katana through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Katana integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Katana connection logic from agent behavior for testable, maintainable code

Katana + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Katana MCP Server delivers measurable value.

Type-safe data pipelines: query Katana with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Katana tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Katana and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Katana responses and write comprehensive agent tests

Katana MCP Tools for Pydantic AI (11)

These 11 tools become available when you connect Katana to Pydantic AI via MCP:

create_sales_order

Requires a customer ID. Create a new sales order

get_inventory_by_variant

Get inventory levels for a specific variant

get_sales_order

Get details for a specific sales order

list_customers

List all customers

list_inventory

List overall inventory status

list_manufacturing_orders

List all manufacturing orders

list_materials

List all materials in Katana

list_products

List all products in Katana

list_purchase_orders

List all purchase orders

list_sales_orders

List all sales orders

list_suppliers

List all suppliers

Example Prompts for Katana in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Katana immediately.

"Show me all active sales orders in Katana."

"Check the inventory level for variant ID 'VAR_987'."

"List all my manufacturing orders."

Troubleshooting Katana MCP Server with Pydantic AI

Common issues when connecting Katana to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Katana + Pydantic AI FAQ

Common questions about integrating Katana MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Katana MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.