Educational Tutor

Provides an MCP server that exposes AI-generated educational courses derived from documentation repositories for interactive tutoring.

python

GitHub Stars

python

Language

6 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "moarshy-mcp-tutor": {
      "command": "/path/to/tutor/project/.venv/bin/uv",
      "args": [
        "--directory",
        "/path/to/tutor/project",
        "run",
        "mcp_server/main.py"
      ],
      "env": {
        "COURSE_DIR": "PLACEHOLDER or actual path to course_output"
      }
    }
  }
}

Educational Tutor provides an MCP server that exposes AI-generated, structured educational courses derived from documentation repositories. It standardizes access to these courses so AI tutors and assistants can fetch, present, and interact with learning content consistently across tools and platforms.

How to use

You access the educational courses through an MCP client by selecting the Educational Tutor MCP Server and connecting to the local or remote server. Use the server to browse, fetch, and interact with course content generated from documentation. You can run the server locally, then initiate learning sessions via your MCP-enabled tutor or assistant.

How to install

Prerequisites: ensure you have Python and a compatible shell installed on your system. You will also use a fast Python package tool abbreviated as uv to manage dependencies.

python -m uv venv
.venv/bin/uv pip install -e .

# Generate courses from documentation
.venv/bin/uv run python course_content_agent/test.py

# Start the MCP server (uses the generated courses by default)
.venv/bin/uv run python -m mcp_server.main

# Or customize the course directory
COURSE_DIR=your_course_output .venv/bin/uv run python -m mcp_server.main

# Test MCP integration from the client perspective
.venv/bin/uv run python mcp_server/stdio_client.py

Configuration, security, and notes

Configure the server to point to your generated courses and control access through the environment and runtime options documented below. Security considerations include keeping your COURSE_DIR private and controlling who can connect via your MCP client. When testing locally, use a dedicated virtual environment and avoid exposing the server to untrusted networks.

Cursor integration is supported via a small configuration file that declares how to start the MCP server from your project, including the directory where courses are located. Use the example below as a template and adjust paths to your environment.

{
  "mcpServers": {
    "educational_tutor": {
      "command": "/path/to/tutor/project/.venv/bin/uv",
      "args": [
        "--directory",
        "/path/to/tutor/project",
        "run",
        "mcp_server/main.py"
      ],
      "env": {
        "COURSE_DIR": "/path/to/tutor/project/course_output"
      }
    }
  }
}

Built by

VeilStrat

AI signals for GTM teams