Canix MCP Server - Setup & Getting Started Guide

Table of Contents

• Overview
• What You Can Do
• What You Need
• Setting Up with Claude
• Setting Up with ChatGPT
• Using the Integration
• Example Questions to try
• FAQs
• Troubleshooting

Overview

The Canix MCP Server lets you connect Canix to AI tools like Claude and ChatGPT using the Model Context Protocol (MCP). Once connected, you can ask natural language questions about your Canix data and get instant answers — no exports or manual lookups required.

Beta Release: Our server covers Sales, Inventory (including non-cannabis inventory), Purchasing, Manufacturing, Lab Tests, Labor, and Cultivation reporting. Additional data types are coming in future releases.

Available data: The server can answer questions about your sales orders, inventory (cannabis and non-cannabis), purchase orders, manufacturing runs, lab test results, labor, and cultivation — and it can combine these in a single question. For example: "which input lots produce our highest-potency products?" or "which supplies will run out before I can reorder?" For the full set of example questions across all areas, see Questions the Canix MCP Server Can Answer.

Example visual response for: 'Give me total revenue, orders, top customers, and sales rep performance'

What You Can Do

• Ask questions like "Show me my top-selling products this month"
• Query sales, inventory, purchasing, manufacturing, lab test, and labor data across your facilities
• Check stock levels, package details, and vendor performance
• Combine sales, inventory, and purchasing in one question (e.g. velocity vs. stock, customer profitability by margin, supplier availability for fast movers)
• Get instant summaries and breakdowns without leaving your AI tool
• Track non-cannabis supplies: stock below PAR, runout timing, and usage costs
• Review production yield, waste, bottlenecks, and trace a lot through to finished goods
• Check pass rates, potency, and COA status across your lab results
• See where labor hours and labor dollars are going

What You Need

• A Canix account
• Claude (desktop or web app) or ChatGPT

Setting Up with Claude

Step-by-Step Instructions

1. Open Claude and go to Settings — click your profile icon in the top-right corner and select Settings.
2. Navigate to the Custom section — in the left sidebar, click on Custom.
3. Click "+ Add" in the top right — then select Add custom connector.
4. Enter a name for the connector — we recommend "Canix" so it's easy to identify.
5. Enter the Canix MCP server URL:

   https://mcp.canix.com/mcp

6. Click Add to save — Canix will now appear in your connectors list.

Tip: You'll be prompted to authenticate with your Canix account the first time you use the connector in a conversation.

Setting Up with ChatGPT

Step 1: Enable Developer Mode

ChatGPT requires Developer Mode to be enabled before you can add custom MCP apps.

1. Open ChatGPT and go to Settings
2. Click on Apps in the left sidebar
3. Click Advanced settings
4. Toggle on Developer Mode (note: OpenAI marks this as Elevated Risk, as it allows unverified connectors)

Step 2: Create the Canix App

1. Go back to Settings → Apps
2. Click Create app
3. Enter a name (e.g. "Canix")
4. Set the Server URL to:

   https://mcp.canix.com/mcp

5. Set Authentication to OAuth
6. Check the acknowledgment box and click Create

Note: OpenAI will display a warning that custom MCP servers introduce risk, as they have not been reviewed by OpenAI. Check the acknowledgment box to proceed.

Using the Integration

Once connected, you can start querying your Canix data directly in conversation. Here are a couple of examples of what answers look like:

"Who are our top vendors by spend this year?" The MCP server ranks vendors by total procurement spend, so you can see your largest suppliers and identify spending concentration at a glance: 


 "Which products are selling fastest, and do we have enough stock to keep up?" The MCP server combines sales velocity with current inventory, flagging reorder opportunities and stockout risks across your fastest movers—demonstrating how you can bridge sales, inventory, and purchasing data in a single query:

More Example Questions to Try

• "What were my total sales last month?"
• "Show me my top 10 products by revenue this quarter."
• "Which customers placed the most orders in the last 30 days?"
• "Break down sales by facility for this week."
• "What products did I sell most of yesterday?"
• "Which non-cannabis products are below their PAR level?"
• "What was our extraction yield last quarter, actual versus planned?"
• "What is my compliance testing pass rate?"
• "Which facilities spend the most on labor?"

You can ask follow-up questions to drill deeper into any result — the AI remembers context within the conversation.

Tips for Best Results

• Be specific about time ranges (e.g. "this month", "last 30 days", "Q1 2026")
• Mention your facility name if you have multiple locations
• Ask follow-up questions — the AI remembers context within a conversation
• Combine domains for smarter questions: pair sales velocity with inventory (reorder planning) or with purchasing (vendor analysis and spending patterns)

Frequently Asked Questions

Will the server maintain memory of prior conversations?

No — the MCP server itself stores no memory. Memory is handled entirely by the AI assistant you're using (Claude, ChatGPT, Gemini, etc.) and only persists within a single conversation. If Canix introduces a native chat UI in the future, we'll add a memory mechanism at that point.

Will data be limited to my currently selected licenses, or all licenses in my environment?

You'll have access to data from all facilities your Canix account has permission to view. You can narrow the scope at any time just by mentioning it in your message — for example: "Generate a sales report just for my distribution facilities."

Can the model present data across all Canix-integrated licenses at the state or national level?

Yes — if your account has access to multiple licenses across locations, you can query and report across all of them.

Will the MCP server's answers respect my user permissions?

Yes — the MCP server enforces Canix's existing user access controls. You will only be able to query data that your account has permission to view.

Are demo and sandbox facilities included?

Not by default. The assistant leaves them out of company-wide totals so practice data doesn't skew your numbers. If a total looks off, ask whether demo facilities were included. You can also ask about one by name, or ask for a list of all your facilities.

Why can't I see labor or NCI costs?

Cost data follows the same permissions as the app. If you don't have the labor cost or NCI cost permission, Claude or ChatGPT will share what you can see and let you know what it left out.
 

Troubleshooting