MCP Educational Tutor

An intelligent tutoring server that uses GitHub documentation repositories to provide structured educational prompts and tools.

An experimental system that transforms documentation repositories into interactive educational content using AI and the Model Context Protocol (MCP).

This project consists of two main components:
- 📚 Course Content Agent- Generates structured learning courses from documentation repositories
- 🔧 MCP Educational Server- Provides standardized access to course content via MCP protocol

Documentation Repository → Course Content Agent → Structured Courses → MCP Server → AI Tutors

The system processes documentation, creates educational content, and exposes it through standardized tools for AI tutoring applications.

tutor/ ├── course_content_agent/ # AI-powered course generation from docs │ ├── main.py # CourseBuilder orchestration │ ├── modules.py # Core processing logic │ ├── models.py # Pydantic data models │ ├── signatures.py # DSPy LLM signatures │ └── about.md # 📖 Detailed documentation ├── mcp_server/ # MCP protocol server for course access │ ├── main.py # MCP server startup │ ├── tools.py # Course interaction tools │ ├── course_management.py # Content processing │ └── about.md # 📖 Detailed documentation ├── course_output/ # Generated course content ├── nbs/ # Jupyter notebooks for development └── pyproject.toml # Project configuration

1. Install Dependencies and Create Virtual Environment

This project usesuvfor fast Python package management.

# Create a virtual environment python -m uv venv # Install dependencies in editable mode .venv/bin/uv pip install -e .

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

Customize for Your Repository: Editcourse_content_agent/test.pyto change:

- Repository URL (currently uses MCP docs)
- Include/exclude specific folders
- Output directory and caching settings

# Serve generated courses via MCP protocol .venv/bin/uv run python -m mcp_server.main # Or customize course directory COURSE_DIR=your_course_output .venv/bin/uv run python -m mcp_server.main

# Test server capabilities .venv/bin/uv run python mcp_server/stdio_client.py

For comprehensive information about each component:

-

Course Content Agent: Seecourse_content_agent/about.md

MCP Educational Server: Seemcp_server/about.md

{ "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" } } } }

- Create a virtual environment:python -m uv venv
- Install dependencies:.venv/bin/uv pip install -e .
- Update thecommandpath and the path inargsto your project directory.
- Restart Cursor or reload the window.
- Use@educational-tutorin Cursor chat to access course tools.

- Course generation from documentation repositories
- MCP server for standardized content access
- Multi-complexity course creation (beginner/intermediate/advanced)

- Support for diverse content sources (websites, videos)
- Advanced search and recommendation systems
- Integration with popular AI platforms

- AI Framework: DSPy for LLM orchestration
- Content Processing: Multiprocessing for performance
- Protocol: Model Context Protocol (MCP) for standardization
- Models: Gemini 2.5 Flash for content generation
- Data: Pydantic models for type safety

This project is experimental and intended for educational and research purposes.

Semantic search over 4.6M+ text chunks from 20,000+ classical philosophy and humanities works — Plato, Aristotle, Kant, Nietzsche, and thousands more. Multilingual (Greek, Latin, German, French, English). No install needed.

Access documentation from the Awesome-llms-txt repository directly in your conversations.

Study the Bible in its original languages, trace themes across both testaments, and compare five translations — all in one conversation. Ask any question about what Scripture says and get grounded, cited answers: What does the Bible say about suffering? Topical search surfaces Job as the Bible's principal witness on suffering (with explanations of why it matters and suggested starting passages), Psalms on lament, Romans on justification — whole books and narratives alongside individual verses. What is the Hebrew word behind lovingkindness in Psalm 23? Compare how KJV and WEB translate John 3:16. Trace the word grace through Paul's letters. Covers 155,510 verses across KJV, WEB, ASV, YLT, and Darby with 606,140 cross-references, 17,543 Strong's entries, BDB and Thayer lexicon definitions, and Nave's 5,319 topical categories.

The Ultimate Math Engine - Unifying SymPy, NumPy & Matplotlib in one powerful server! Perfect for devs & researchers.

Search and analyze classical Japanese literature using the Genji API, with advanced normalization features.

MidOS Research Protocol: curated skills & knowledge versioned.

Search Recon documentation, book, and newsletter for fuzzing, invariant testing, and Chimera framework knowledge

Provides access to Jewish texts from the Sefaria library.

Search and retrieve technical documentation for T&M, industrial automation, and power electronics. Covers everything from oscilloscopes, microcontrollers, vehicles, power supplies, and more from a wide range of manufacturers.