An experimental system that transforms documentation repositories into interactive educational content using AI and the Model Context Protocol (MCP).
Mcp tutor mcp server connects MCP Tutor to AI assistants that speak the Model Context Protocol. An experimental system that transforms documentation repositories into interactive educational content using AI and the Model Context Protocol (MCP).
An experimental system that transforms documentation repositories into interactive educational content using AI and the Model Context Protocol (MCP).
Once connected, the assistant can call these 4 tools directly:
Multi — complexity course creation (beginner/intermediate/advanced)Protocol — Model Context Protocol (MCP) for standardizationModels — Gemini 2.5 Flash for content generationData — Pydantic models for type safetySetup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.
The server reads one environment variable: COURSE_DIR. Keep credentials in your client's env block or a secrets manager rather than committing them.
Knowledge and memory servers address the most frustrating trait of language models — walking into every conversation with no recollection of the last one. MCP Tutor sits in that group, and the shape of its toolset — Multi, Protocol, Models among others — tells you what it is really for. Worth comparing against the other knowledge memory servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.
| Tool | What it does |
|---|---|
| Multi | complexity course creation (beginner/intermediate/advanced) |
| Protocol | Model Context Protocol (MCP) for standardization |
| Models | Gemini 2.5 Flash for content generation |
| Data | Pydantic models for type safety |
{
"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"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| COURSE_DIR | Filesystem location the server is allowed to use. | Optional |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.