FAQ
AROYA MCP frequently asked questions
About the AROYA MCP
The AROYA MCP lets you ask questions about your facility in plain English inside an AI assistant like Claude or ChatGPT, and get answers pulled live from your AROYA data. MCP stands for Model Context Protocol, an open standard that lets AI assistants connect securely to outside data sources. AROYA hosts the connection for you: add it to your assistant once and sign in with your AROYA account.
Anyone with an AROYA login, including growers, cultivation directors, and operations and executive teams. If you can see it in AROYA, you can ask about it.
It's free during the introductory period. Customers who sign up before December 31, 2026 will receive free access until their 2027 renewal date. After renewal, you access will require a subscription fee of $25 per facility per month. Your account manager will share details before anything changes.
No. The AROYA MCP is read-only. It reads your data and never changes it, so it can't edit schedules, create tasks, or adjust setpoints. Write capabilities are being evaluated for a future release.
Claude and ChatGPT are officially supported and tested. The same connection may work in other MCP-compatible tools, but AROYA Support can only help with Claude and ChatGPT.
Getting connected
Three things: an active AROYA login, an AI assistant plan that allows connectors, and the MCP feature turned on for your facility. If you're not sure the feature is on, ask your AROYA account manager or Support to enable it.
In your assistant's connector or integration settings, add a new custom connector, name it (for example, "AROYA"), and paste the server address from your setup instructions. When prompted to sign in, use the same email address you use to log in to AROYA. For screenshots and a short video, follow the AROYA MCP quickstart guide.
Most paid plans do. Here's how each one works:
- Claude Free:Yes, but only one custom connector is allowed. Remove an existing connector if the slot is taken.
- Claude Pro and Max:Yes.
- Claude Team and Enterprise:Yes, once your account owner or admin enables it.
- ChatGPT Free:No. Connectors aren't available on the free tier.
- ChatGPT Plus, Pro, Business, Enterprise, and Edu:Yes, through Developer Mode. On Business, Enterprise, and Edu workspaces, your admin must allow or register the connector first.
Open your assistant's list of connected apps and confirm AROYA appears. Then start a chat and ask, "Which AROYA facilities can I see?" If it lists your facilities, you're connected.
Yes. Each person adds the connector to their own AI assistant and signs in with their own AROYA email. Everyone sees only what their AROYA permissions allow.
What you can ask
Nearly everything in your AROYA account that you have permission to view: substrate and climate readings (water content, pore EC, temperature, humidity, VPD, and light), irrigation events and schedules, rooms, zones, and harvest groups, target ranges, alerts, journal entries, tasks, harvest records, and device and gateway status. The one exception is images. Photos attached to scouting notes, tasks, or SOPs aren't available.
Specific questions about a room, zone, or harvest group over a defined time window. Try these to start:
- "What is the current water content and EC in Flower 4?"
- "How many irrigation shots did Zone 2 in Veg 1 receive yesterday, and what was the total volume?"
- "Show me the overnight dryback for each zone in Flower 2 over the last 7 days."
- "Which rooms had VPD outside their target range this week?"
- "Compare average pore EC between Flower 1 and Flower 3 for the current harvest group."
- "List any sensors or gateways that have gone offline in the last 24 hours."
- "Summarize this week's journal entries for Flower 4."
Yes. Once the basics work, ask it to compare harvest groups, find which irrigation or climate variables moved alongside yield, or write a daily morning summary for one room. For heavier analysis, use your assistant's most capable model (for example, Claude Opus) and keep the question scoped to a few rooms and a defined period.
If your AI assistant supports scheduled tasks (for example, Claude Cowork), you can schedule a prompt like "Every morning at 6 AM, summarize overnight conditions and irrigation for Flower 1 through Flower 4" and have it delivered to you automatically.
Yes. If your environmental controls, ERP, or compliance system also offers an MCP connector, add both to the same assistant and ask questions that span them, like relating fan speeds or room setpoints to substrate readings.
Yes. AROYA API keys can be used to build a custom connector. Most customers prefer the hosted AROYA MCP because AROYA maintains it, it needs no hosting, and it comes with purpose-built tools for cultivation questions.
Permissions, access, and security
Exactly what they can see in AROYA today. The MCP enforces your existing AROYA user permissions, including facility membership and harvest group access. A user whose AROYA role only covers tasking can only ask about tasking data.
Through secure OAuth sign-in with your AROYA email. Your AROYA password is never shared with the AI assistant, and the connection can be revoked at any time from your assistant's connector settings or by your AROYA administrator.
The assistant retrieves only the data needed to answer each question, at the moment you ask. AROYA doesn't bulk-export your data to Anthropic or OpenAI. How your assistant stores conversation history depends on your plan and settings with that provider; Team and Enterprise plans typically exclude data from model training. Learn more about how AROYA secures your data.
Yes. You can manage which members of your facility can access the AROYA MCP through the Manage role option on the Settings > Staff page in AROYA.
Accuracy and limitations
Yes. The MCP reads from the same database the app uses, so there's no separate copy that can drift. If a figure looks different, it's almost always one of three things: the app rounds or smooths values on charts while the assistant reports raw values, the time window or zone in your question wasn't the one you had in mind, or the assistant averaged several readings. Ask it to show the exact readings and time range it used, then compare against the same view in the app.
Yes. The AI assistant can misread a question, pick the wrong room, or draw a conclusion the data doesn't support. Every AROYA MCP conversation carries the reminder "AROYA can make mistakes. Please double-check responses." Treat its answers the way you'd treat a sharp new team member's: useful, fast, and worth verifying before you act on anything important. The AROYA app remains your source of truth.
Think of the MCP as the part that fetches data and the AI model as the part that interprets it. If the assistant returns no data, says it can't see a facility, or reports a connection error, the issue is on the AROYA or connector side. If the data is right but the summary, math, or recommendation is off, that's the AI model's interpretation. Rephrase with a specific room, zone, metric, and dates, or ask it to list the data behind its answer.
The current version can't:
- Write or change anything in AROYA, including schedules, tasks, setpoints, or notes.
- Show photos or images attached to tasks, scouting notes, or SOPs. Open those in the AROYA app.
- Answer questions about facilities you don't have access to.
- Replace AROYA alerts or notifications. It answers when asked rather than watching continuously.
- Guarantee fast responses on very broad questions, like every facility across all history.
Yes, on two fronts. AROYA will keep adding tools and data to the connector, and the AI models themselves keep improving, so the same connection will handle harder questions over time.
Troubleshooting
Usually the email doesn't match your AROYA login, or the MCP feature isn't enabled for your facility yet. Sign in with the exact email you use for AROYA. If that matches, ask your account manager to confirm the feature is enabled.
The connector is likely turned off in the assistant, or your plan doesn't allow connectors (ChatGPT Free, or a Claude Free slot that's already in use). Check the assistant's connected-apps list and plan limits, and remove an unused connector on Claude Free.
Your sign-in session probably expired, or the connector was toggled off. Open the connector settings and reconnect or sign in again.
The question is likely too broad (every facility, months of history) and needs many data pulls. Narrow it to one or two rooms and a defined window. Use a faster model (for example, Claude Sonnet) for quick lookups, and save the most capable model for deep comparisons.
You don't have access to it in AROYA. Ask your facility administrator to update your AROYA permissions, and the connector will pick up the change automatically.
Email support@aroya.io with:
- The AI assistant and plan you use (for example, Claude Pro or ChatGPT Business)
- Your facility name
- The exact question you asked and what the assistant replied
- A screenshot
Connection problems that aren't caused by the AROYA feature setting usually sit inside your Claude or ChatGPT settings, and Support can help you tell the two apart.
Tips for better results
- Be specific.Name the facility, room or zone, metric, and time window. "Average dryback in Flower 2, Zone 3, last 5 days" beats "How is Flower 2 doing?"
- Start narrow, then widen.Ask about one room first, confirm the answer matches the app, then ask the assistant to repeat the analysis for other rooms.
- Ask for the evidence.Phrases like "show the readings you used" or "list the irrigation events behind that total" make answers easy to verify.
- Match the model to the job.Use fast models for quick lookups and daily summaries, and the most capable model for multi-room comparisons and yield-driver analysis.
- Use follow-ups.The assistant remembers the conversation, so you can say "now do the same for Flower 3" or "chart that by day" without restating everything.
- Save prompts that work.Keep a note of questions that give you useful answers, reuse them each morning, or turn them into a scheduled report.
Setup steps and video are in the AROYA MCP quickstart guide. Send feature requests, favorite use cases, and anything that didn't work to your account manager or AROYA Support. What customers ask for shapes what gets added next.