litmos-mcp
Read-only MCP server for Litmos LMS that exposes user profiles, course results, and training completion data to AI clients.
README
litmos-mcp
An MCP server that provides read-only access to the Litmos LMS REST API. Expose training completion status, user profiles, course results, and learning path data to any MCP-compatible AI client.
Prerequisites
- Python 3.11+
uvinstalled- A Litmos API key (Account Owner access required)
Quick start
Run directly from GitHub
LITMOS_API_KEY=your_key uvx --from git+https://github.com/dbuxton/litmos-mcp litmos-mcp
Run from a local clone
git clone https://github.com/dbuxton/litmos-mcp
cd litmos-mcp
LITMOS_API_KEY=your_key uvx --from . litmos-mcp
Configuration
All configuration is via environment variables:
| Variable | Required | Default | Description |
|---|---|---|---|
LITMOS_API_KEY |
Yes | — | Your Litmos API key |
LITMOS_REGION |
No | us |
API region: us, eu, or au |
LITMOS_SOURCE |
No | litmos-mcp |
Source label sent with every API request |
Region endpoints
| Region | Base URL |
|---|---|
us |
https://api.litmos.com/v1.svc |
eu |
https://api.litmoseu.com/v1.svc |
au |
https://api.litmos.com.au/v1.svc |
MCP client configuration
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"litmos": {
"command": "uvx",
"args": ["--from", "git+https://github.com/dbuxton/litmos-mcp", "litmos-mcp"],
"env": {
"LITMOS_API_KEY": "your_key_here",
"LITMOS_REGION": "us"
}
}
}
}
Claude Code
claude mcp add litmos \
--command uvx \
--args "--from,git+https://github.com/dbuxton/litmos-mcp,litmos-mcp" \
--env LITMOS_API_KEY=your_key_here
Or add directly to .claude/mcp.json in your project:
{
"mcpServers": {
"litmos": {
"command": "uvx",
"args": ["--from", "git+https://github.com/dbuxton/litmos-mcp", "litmos-mcp"],
"env": {
"LITMOS_API_KEY": "your_key_here"
}
}
}
}
Available tools
| Tool | Description |
|---|---|
litmos_search_users |
Search users by name, email, username, or company |
litmos_get_user |
Retrieve a full user profile by encrypted user ID |
litmos_list_users |
List all users with pagination support |
litmos_get_user_courses |
Get all courses assigned to a user with completion status |
litmos_get_user_course_results |
Get module-level results for a specific user/course pair |
litmos_get_user_learning_paths |
Get learning paths assigned to a user |
litmos_list_courses |
List all courses in the organisation |
litmos_get_user_teams |
Get teams a user belongs to |
Typical workflow
- Find a user — use
litmos_search_userswith a name or email to get their encryptedId. - Check training — use
litmos_get_user_courseswith thatIdto see all assigned courses and completion status. - Drill into a course — use
litmos_get_user_course_resultswith the userIdand courseIdfor module-level scores and attempt counts.
API notes
- The Litmos REST API enforces a limit of 100 requests per minute per API key. The server surfaces a clear error if this is exceeded.
- All tools are read-only — no write operations are exposed.
- Encrypted IDs returned by list/search endpoints must be used verbatim with other tools; do not attempt to decode or construct them manually.
Development
git clone https://github.com/dbuxton/litmos-mcp
cd litmos-mcp
uv sync
LITMOS_API_KEY=your_key uv run litmos-mcp
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.