Skip to main content
Glama
README.md
# courseatlas

A map to a free AI curriculum that lives somewhere else. courseatlas is a local forwarding client for the hosted AI School MCP service: it answers `tools/list` on your own machine from the captured tool definitions and forwards every search and read to AI School, returning the answers exactly as the service sends them back.

The surface is entirely read-only. You can search the lesson catalogue, browse the course tracks, open one track to see how it is structured, and pull the full text of a single lesson. Nothing is mirrored, cached or stored locally — the package is a well-behaved doorway, not a copy of the school.

## The tools

- **`search_lessons`** — Search the AI School curriculum (500+ tracks, thousands of free lessons on AI engineering, governance, security, and applied AI by profession) and get back matching lesson titles and URLs. `query` is required; `limit` caps the results (default 10, max 50).
- **`list_tracks`** — List the course tracks, optionally narrowed by a substring of the title or slug. Takes an optional `filter` and a `limit` (default 40, max 200); both may be omitted.
- **`get_track`** — One track with its full lesson list, so you can see the structure of a course before choosing what to read. `slug` is required.
- **`read_lesson`** — The full text of a lesson, fetched by the URL that `search_lessons` or `get_track` returned, as readable markdown-ish text with headings and code blocks. `url` is required.

## Install and run

As an MCP server via npm:

```bash
npx -y @reneturcios/courseatlas mcp
```

MCP client configuration:

```json
{
  "mcpServers": {
    "courseatlas": {
      "command": "npx",
      "args": ["-y", "@reneturcios/courseatlas", "mcp"]
    }
  }
}
```

As a container:

```bash
docker run -i ghcr.io/cloudcorprecords/courseatlas
docker run --rm ghcr.io/cloudcorprecords/courseatlas list_tracks '{}'
```

## CLI

One binary serves both the command line and the MCP server. Each tool is a subcommand taking a single JSON string with that tool's arguments:

```bash
courseatlas search_lessons '{"query":"prompt injection defence"}'
courseatlas list_tracks '{"filter":"security"}'
courseatlas get_track '{"slug":"rag"}'
courseatlas read_lesson '{"url":"https://lillytechsystems.com/lessons/rag-basics"}'
courseatlas --version
```

Exit codes: `0` when the forwarded call succeeds, `1` when the upstream result is an error, and `2` for usage problems such as an unknown subcommand or a malformed JSON argument.

## Configuration

- `LILLYTECHSYSTEMS_MCP_URL` — Overrides the upstream endpoint. The default is the pinned hosted endpoint, `https://lillytechsystems.com/mcp`. (The override variable is a reconstruction added by this rebuild.)

The AI School registry record declares no headers on its remote, so courseatlas sends no authentication header of any kind — the catalogue is free and the client is keyless.

Upstream failures — a JSON-RPC error from the service, a non-2xx response, an unreadable body, or a request that fails outright — are reported to the caller as an error result whose text starts with `courseatlas error:`.

## How forwarding works

The first forwarded call opens a session: an `initialize` request (protocol version `2025-03-26`), followed by a `notifications/initialized` notification, then the `tools/call` itself. If the service answers the initialize request with an `Mcp-Session-Id` header, that value is carried on every later request, and the open session is reused for the rest of the process. Replies are accepted either as plain JSON or as server-sent events. Successful results pass through verbatim, including any `isError` flag and any extra fields the service includes.

## Development

```bash
npm install
npm run build   # tsc -> dist/ (dist/cli.js is the bin)
npm test        # tsx --test test/*.test.ts — stubbed upstream, no network
npm run dev     # run the CLI from source
```

The test suite checks the served tool list against the captured surface, exercises the session handshake and its reuse, asserts that no `Authorization` header is sent under any environment, and verifies that arguments go upstream untouched and results come back untouched.

## License

MIT — see `LICENSE`. Copyright (c) 2026 Rene Turcios.