This functionality is part of the Schoox Intelligent Learning Platform and is available to all customers at no additional cost. If you do not see these features in your academy, reach out to support or your customer success representative.
The Public MCP (Model Context Protocol) Server makes it possible to connect your organization's AI assistant of choice to your academy, allowing you to use natural language to query users, courses, enrollments, progress, events, and more -- without writing API code. It essentially allows an admin the ability to run specific reporting directly from your AI assistant.
The MCP does not connect to LINA.
Important Note:
This version of the MCP Server retrieves data and does not make any actions in your academy. It can be used only for reporting needs.
Prerequisites for the MCP Server to work
What you need:
- Node.js
- Node.js version 18 or newer installed on your computer (get it here)
* Node.js is important to be installed for the process to run properly.
- Claude Desktop
- Go to https://claude.com/download, download Claude Desktop and install it to your device.
- Academy ID and API Key
You will also need to obtain the following before proceeding:
- Schoox academy API Key
- Schoox Academy ID
This can be found under the Academy Workspace
Then go to Academy Admin > Configuration > General > Api Key tab
In that page you can find the Academy ID and the API Key to be added to the config file.
If the API Key page is not presented please reach out to Schoox Support to have it enabled in your Academy.
Setting up Claude Desktop with the Schoox MCP Server
Open Claude Desktop and go to File → Settings → Developer (or similar, depending on version) — there's an "Edit Config" button there.
Click it the “Edit Config” button, then open the file it points to (right-click the file and choose to edit it with Notepad or a similar text editor). The file should be the claude_desktop_config.json one
Remove all the content found in the file
Add the following parameters to the file, after the first bracket ({), replacing the API Key ("your-api-key") and Academy ID (“123456”) with your own as found in the API Key page of your academy.
{
"mcpServers": {
"schoox": {
"command": "npx",
"args": ["-y", "@schoox/schoox-mcp-server"],
"env": {
"SCHOOX_API_KEY": "your-api-key",
"SCHOOX_ACADEMY_ID": "123456"
}
}
}
}Hit File -> Save into the text editor
Restart Claude Desktop (Exit from the taskbar)
Once Claude Dekstop opens, you can check that it’s configured correctly under “Customize” -> Developer:
Test the Schoox Connector in Claude Desktop
Type in the chat “is the schoox connector enabled?”
Claude Desktop should reply back “Yes — the Schoox connector is available.”
Uses
Once configured, ask your AI assistant questions like:
- "Show me all active courses in my academy"
- "How many users completed the Safety Training course this month?"
- "List all events scheduled for next week"
The assistant uses the Schoox MCP tools automatically to fetch data from your academy and respond in natural language.
Your AI assistant should be able to help with the following:
- Look up organizational hierarchy levels above units (regions, divisions, areas, districts)
- List available badges configured in the academy
- Browse content items (web resources, uploaded files, SCORM packages) and metadata
- Query the course catalog, course details, skills, students, lectures, and exams
- Query learning paths (curricula) -- structured training programs
- Training analytics and progress reporting (per-user and aggregate)
- Query instructor-led training (ILT) and virtual classroom (VC) events
- Query exam metadata and student exam results/scores
- List user groups configured in the academy
- List job roles defined in the academy
- Query skill/competency definitions, assessments, and relationships
- List custom type definitions configured in academy settings
- Look up organizational units (stores, locations, departments)
- Get academy-wide usage and licensing summary statistics
- Look up user profiles and badges
Settings you can adjust (optional):
| Setting | Required? | Default | What it does |
|---|---|---|---|
| SCHOOX_API_KEY | Yes | — | Your Schoox API key |
| SCHOOX_ACADEMY_ID | Yes | — | Your numeric Academy ID |
| SCHOOX_MAX_RECORDS | No | 1000 | Most records returned per request |
| SCHOOX_BASE_URL | No | https://api.schoox.com/v1 | The API address the server talks to |
Other Setups (if not using Claude Dekstop)
Claude Code
Add the same kind of entry to ~/.claude.json (applies to all projects) or to a .mcp.json file in your project folder (applies to just that project):
{
"mcpServers": {
"schoox": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@schoox/schoox-mcp-server"],
"env": {
"SCHOOX_API_KEY": "your-api-key",
"SCHOOX_ACADEMY_ID": "123456"
}
}
}
}Or, instead of editing a file, just run this command:
claude mcp add schoox -e SCHOOX_API_KEY=your-api-key -e SCHOOX_ACADEMY_ID=123456 -- npx -y @schoox/schoox-mcp-server
Cursor
Add the same entry to ~/.cursor/mcp.json (applies to all projects) or .cursor/mcp.json in your project folder (applies to just that project):
{
"mcpServers": {
"schoox": {
"command": "npx",
"args": ["-y", "@schoox/schoox-mcp-server"],
"env": {
"SCHOOX_API_KEY": "your-api-key",
"SCHOOX_ACADEMY_ID": "123456"
}
}
}
}Any other MCP-compatible assistant
Use the same setup shown above — it works the same way across MCP clients.
Data Privacy
This server exposes sensitive Schoox data. The API returns user PII (names, emails, employment data) and corporate confidential information (training records, org structure, business data). Any data the MCP tools retrieve flows through your connected AI assistant.
When you use this server with an AI client (Claude Desktop, Claude Code, Cursor, etc.), data returned by the tools is transmitted to your AI provider's servers as part of the conversation. Depending on your account type and your provider's policies, that data may be retained, logged, or used for model training (for example, on free or consumer-tier accounts). Review your AI provider's data usage and retention policies, and prefer accounts or plans with appropriate data protections (such as commercial or enterprise terms that guarantee no training on your data) before connecting this server to production academy data.
Disclaimer: Schoox is not responsible for any data leaks, data exposure, or misuse of data resulting from use of this tool. Responsibility for compliance with your organization's data handling policies and applicable privacy regulations rests with you.
For additional information, please see Schoox's AI Functionality Policy.