LearnMCP-xAPI

Name: LearnMCP-xAPI
Author: DavidLMS

@DavidLMS

About LearnMCP-xAPI

An open-source MCP (Model Context Protocol) server that enables AI agents to record and retrieve learning activities through xAPI-compliant Learning Record Stores

#learnmcp #xapi #education #ai #learning

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "learnmcp-xapi": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        "learnmcp-env"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is LearnMCP-xAPI?

LearnMCP-xAPI is an open-source MCP (Model Context Protocol) server that enables AI agents to record and retrieve learning activities through xAPI-compliant Learning Record Stores. It creates a bridge between AI interactions and learning analytics, allowing intelligent systems to build contextual understanding of what learners know, practice, and achieve. It is designed for developers building AI tutoring systems, personalized learning assistants, or educational analytics platforms.

How to use LearnMCP-xAPI?

Install by cloning the repository and installing dependencies (Python 3.8+ required). Configure by copying .env.example to .env and setting your LRS plugin (e.g., lrsql, ralph, veracity), student identifier (ACTOR_UUID), and LRS credentials. Then use with an MCP-compatible client like Claude Desktop. The server exposes three core tools via MCP: statement recording, progress retrieval, and activity vocabulary management.

Key features of LearnMCP-xAPI

xAPI 1.0.3 compliance for interoperability with educational ecosystems.
Native MCP integration for seamless AI agent connectivity.
Plugin architecture supporting multiple Learning Record Stores (LRS SQL, Ralph LRS, Veracity Learning).
Privacy-preserving design using unique student identifiers (ACTOR_UUID).
Intelligent statement generation from natural language learning activities.
Contextual learning queries for adaptive AI responses.
Robust retry logic and error