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
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。