How to Use the Canix ERP MCP in Google ADK

Q: How do I connect the Google ADK to my Canix ERP server?

You'll use the McpToolset class from the Google ADK. Just give it the URL for your Vinkius-hosted Canix MCP server. The toolset is then passed to your LlmAgent, and it's ready to go.

Q: Is it possible to run a Google ADK agent that only reads plant data from Canix ERP?

Absolutely. When you create the McpToolset, you can use the optional toolnames filter. Just provide a list of the read-only tools you want to allow, like 'getplantdetails', 'listplants', and the agent won't see any others.

Connect Gemini to your Canix ERP and analyze operations data at scale with the Google ADK.

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 Google ADK

Create your Vinkius account to connect Canix ERP to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pull Canix Data into BigQuery

Your Gemini agent can now act as a bridge between Canix and your Google Cloud data warehouse. Use the agent to call `list_inventory_packages` and `list_sales_orders`, then feed that operational data directly into BigQuery tables for analysis. It's a straight shot from your ERP to your analytics stack. This isn't just a data dump. You can build agents that react to changes. For instance, an agent could monitor plant batch data via `list_plant_batches` and trigger a Vertex AI pipeline if growth metrics fall outside of your forecasts.

Long-Context Reasoning for Your Canix MCP Server

Gemini's massive context window changes how you work with Canix data. Your agent can ingest a full history of sales orders from `list_sales_orders` in one go. Then, it can reason about trends, seasonality, and customer behavior without making hundreds of separate calls. Imagine asking your agent to "summarize sales performance for the last quarter and cross-reference it with our top-selling cannabis packages." The agent can hold all the data from `get_sales_order` and `get_package_details` in its context to give you a complete answer.

Build Enterprise Agents on Google Cloud

The Google ADK is designed for enterprise use on GCP. You can deploy an agent that monitors your cultivation pipeline by calling `list_plants` and `get_plant_details`. The agent runs securely within your existing Google Cloud environment. You can restrict which tools your agent accesses. The `tool_names` filter in the `McpToolset` lets you expose only read-only tools like `get_account_info`, preventing the agent from performing actions you haven't approved. This is a key control for enterprise deployments that use an MCP server.

Setup guide

Set up Canix ERP MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Canix ERP tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Canix ERP_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Canix ERP tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

You'll use the `McpToolset` class from the Google ADK. Just give it the URL for your Vinkius-hosted Canix MCP server. The toolset is then passed to your `LlmAgent`, and it's ready to go.

Yes, that's exactly what it's for. The Google ADK is part of the Gemini ecosystem. You can use any Gemini model available through Vertex AI to power an agent that interacts with your Canix ERP data.

The main advantage is Gemini's large context window. Your agent can pull huge amounts of data from Canix tools like `list_sales_orders` or `list_inventory_packages` and reason over it in a single prompt, which other models can't do.

Absolutely. When you create the `McpToolset`, you can use the optional `tool_names` filter. Just provide a list of the read-only tools you want to allow, like `['get_plant_details', 'list_plants']`, and the agent won't see any others.

Security is handled by Vinkius and Google Cloud. Your connection to the Canix MCP server is authenticated with a single token. Since the agent runs within your GCP project, all data it pulls—like plant, inventory, or sales order details—is protected by your project's IAM policies and network controls.

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