How to Use the Canix ERP MCP in Pydantic AI

Get type-safe, validated Canix ERP data in your Python agent with 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 Canix ERP MCP to Pydantic AI

Create your Vinkius account to connect Canix ERP 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 Canix ERP with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Never Trust, Always Verify Your ERP Data

Pydantic AI's core principle is runtime validation. When your agent calls `get_package_details`, the JSON response from the Canix server is parsed and validated against a Pydantic model. If a field is missing or has the wrong type, your code gets an immediate, clean `ValidationError`. This means no more silent failures or corrupted data making it into your system. Your agent won't hallucinate a `delivery_status` field on a sales order from `get_sales_order` because the Pydantic model doesn't have one. You build with confidence because the data structure is guaranteed.

Model-Agnostic Canix ERP Agents

Pydantic AI doesn't lock you into a specific LLM provider. You can build an agent that uses `list_plants` and `list_plant_batches` with an OpenAI model today, and switch to a local Llama model tomorrow with a one-line code change. The tool-calling logic remains the same. This freedom lets you choose the right model for the job. Use a powerful model for complex analysis of sales orders and a smaller, faster model for simple inventory lookups with `list_non_cannabis_inventory`. Your agent's core logic, backed by this MCP server, stays constant.

Write Predictable Code for Unpredictable Inputs

Building AI agents means dealing with unpredictable LLM outputs. Pydantic AI brings order to that chaos. When your agent decides to call `get_sales_order`, you know the arguments it provides will match the tool's signature, and the data you get back will match your model. This makes your agent code cleaner and more predictable. Instead of writing defensive code with lots of `if key in dict` checks, you just work with the Pydantic objects. The framework handles all the validation behind the scenes, so you can focus on your business logic.

Setup guide

Set up Canix ERP 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": {
        "canix-erp-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Every response from the Canix MCP server is validated against a Pydantic model at runtime. If the API for `get_package_details` returns data that doesn't match the expected structure, Pydantic AI raises a `ValidationError` immediately instead of letting bad data into your app.

Yes. Pydantic AI is model-agnostic. You can connect it to OpenAI, Anthropic, Google, or a local model you're running yourself. Your agent will be able to call Canix ERP tools like `list_inventory_packages` regardless of the LLM backend.

Your agent will fail loudly and immediately, which is a good thing. If a tool like `get_plant_details` starts returning a new field or changes a data type, Pydantic AI's validation will catch it on the first call. This prevents silent bugs and data corruption.

It's very straightforward. You install the library, create an `MCPToolset` with your server URL, and pass it to your `Agent`. Pydantic AI handles the rest, automatically creating validated tool calls for your agent.

Your data's security is rock-solid. The Vinkius-hosted MCP server uses an ephemeral, zero-trust environment, and your connection is secured by a unique token. Pydantic AI simply processes the data—like plant details, inventory lists, and sales orders—that your authenticated agent requests, and it never leaves your application's memory unless you explicitly code it to.

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