Back to Browse

Courseatlas MCP Server

Developer ToolsModerate5.1MCP RegistryLocal
Free

Server data from the Official MCP Registry

Search and read the free AI School curriculum: lessons, course tracks, full lesson text.

About

Search and read the free AI School curriculum: lessons, course tracks, full lesson text.

Security Report

5.1
Moderate5.1Moderate Risk

courseatlas is a keyless forwarding client that sends every search and lesson-read request to a pinned third-party endpoint (lillytechsystems.com) and returns the responses unchanged. It sends no credentials and has no local shell, file, or code-execution surface, so the main concerns are the data it sends upstream, the trust placed in upstream content, and some provenance ambiguity in the code comments and README. Permissions (network_http, env_vars) match the stated purpose. Supply chain analysis found 3 known vulnerabilities in dependencies (0 critical, 2 high severity). Package verification found 1 issue.

8 files analyzed · 9 issues found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

What You'll Need

Set these up before or after installing:

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.)Required

Environment variable: LILLYTECHSYSTEMS_MCP_URL

How to Install

Add this to your MCP configuration file:

{
  "mcpServers": {
    "courseatlas": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/courseatlas@0.1.0"
      ],
      "env": {
        "LILLYTECHSYSTEMS_MCP_URL": "your-lillytechsystems-mcp-url-here"
      }
    }
  }
}

Some servers take additional arguments. See the repository for details.

Documentation

View on GitHub

From the project's GitHub README.

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:

npx -y @reneturcios/courseatlas mcp

MCP client configuration:

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

As a container:

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:

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

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.

Reviews

No reviews yet

Be the first to review this server!