Last updated: October 28, 2026
When you connect an AI assistant — like Claude or ChatGPT — to your Thinkific school using the Thinkific MCP Server, you're giving that AI the ability to work with your school's data on your behalf. This page explains exactly how that works, what the AI can and can't access, and how your data is protected.
The Thinkific MCP Server uses OAuth 2.0 — the same industry-standard authorization method used by apps like Google, Slack, and Salesforce. When you connect your AI assistant, you go through a one-time authorization flow where you explicitly grant access. Thinkific then issues a secure token that the AI uses to make requests on your behalf.
A few important things to know:
Native read tools, apart from basic account and site details, are limited by the scopes you grant at connection time — specific permissions that control which of those tools can run.
Depending on the scopes you grant, the AI can work with information about:
When Execute is enabled, it is not limited by those OAuth scopes, so it can also reach domains such as community posts and assignment submissions. Gated write actions may also be available via Execute when enabled. Those writes remain subject to Thinkific's mutation policy.
The AI cannot access:
Here's the data flow when you ask an AI to do something with your Thinkific data:
Thinkific controls what data is accessible. Native read tools, apart from basic account and site details, are limited by the scopes you grant. When Execute is enabled, it is not limited by those scopes; writes go through Thinkific's mutation policy.
The AI platform controls what happens in your session. Once data is returned to your AI session, it's governed by that platform's privacy and data handling policies — not Thinkific's. We recommend reviewing your AI provider's privacy policy to understand how session data is handled.
The MCP Server is designed to facilitate the request and return the result without retaining a copy of the data returned during your AI session. Thinkific does not use data from your AI session for any purpose other than fulfilling your request.
When Execute is enabled, the GraphQL document text you send — including string literals in the query — is not included in Mixpanel analytics events. Those events, used to measure product usage, may include the length of the document, operation type, depth, and cost. They may also include root field names as written in the document (not checked against the schema). A field name you write can appear in Mixpanel as Query fields even when Thinkific rejects that field.
Your learner records may contain personally identifiable information (PII) such as names, email addresses, and enrollment history. The Thinkific MCP Server handles this with care:
If your organization has a Data Processing Agreement (DPA) with Thinkific, that agreement applies to personal data accessed through the MCP Server to the extent the MCP Server is part of the Services under your agreement with Thinkific.
Learner data belonging to minors. If your school serves learners under the age of 13, you are responsible for ensuring that connecting an AI integration complies with applicable laws, including the Children's Online Privacy Protection Act (COPPA) and, where applicable, FERPA. You must obtain any required parental consents before authorizing an AI assistant to access learner records that may include data about children under 13. Thinkific does not independently verify the age of learners on your school and does not restrict connector access to minor data at the platform level — that responsibility rests with you as the school operator. If you believe any data relating to a child under 13 has been improperly accessed, please contact [email protected].
Thinkific MCP is designed to return school data to your AI session without retaining a copy. Limited request logs (such as timestamps and your school identifier) are kept for up to 30 days for security and reliability. Limited mutation logs (such as timestamps, your school identifier, your account identifier, and the names of write actions) may be kept for security and reliability.
How long Thinkific retains your data. Thinkific retains learner and school data for the duration of your subscription and for up to 60 days following account termination, after which it is deleted or anonymized in accordance with our Privacy Policy and your Data Processing Agreement with Thinkific. The MCP Server does not create any additional retention of your data beyond these existing periods.
You can revoke access at any time from your Thinkific Connected Apps settings. Once revoked, the token can no longer be used to access your school.
When you connect an AI assistant to your Thinkific school, your data is used for one purpose only: completing the tasks you ask the AI to perform. Nothing more.
Thinkific does not train AI models. The AI model you're using — whether that's Claude, ChatGPT, or another assistant — is a third-party product that Thinkific connects to, not one we build or train. Your course content, learner records, and school data are not used to improve or train any model on our end.
Your data doesn't flow back to Thinkific for AI purposes. When you ask your assistant a question about your school, the assistant sends a request to Thinkific to fetch the relevant data. That data goes back to your assistant to answer your question. Thinkific doesn't receive it back for any other purpose. We don't retain returned school payloads for AI training; limited request and mutation logs (such as timestamps and your school identifier) may be kept for security and reliability, as described under Data retention.
What about the AI provider? The model doing the actual processing — whether that's Claude, ChatGPT, or another assistant — is governed by its own data policies. Most enterprise AI providers, including Anthropic and OpenAI, offer plans that explicitly exclude customer data from model training. We recommend reviewing your AI provider's privacy policy and terms of service to understand how your session data is handled, including whether your data may be used for model training.
Your role as data controller. When you connect your Thinkific school to an AI assistant via the MCP Server, you are the data controller for your learners' personal data. You are responsible for ensuring that your use of any connected AI platform — including the personal data that flows into your AI session — complies with applicable data protection laws and your own privacy obligations to your learners. This includes ensuring your AI provider's terms and data processing agreements are appropriate for the data you are sharing with them. Thinkific's Data Processing Agreement and AI Addendum govern Thinkific's obligations as your data processor; they do not govern the AI platform you connect to.
If you have questions about data privacy, connected apps, or how the MCP Server handles your data, contact [email protected].