ohneben's LearnWorlds MCP

Run your LearnWorlds school in plain language from AI assistants like Claude, Cursor, and any other MCP client.

This Model Context Protocol server exposes the LearnWorlds public API — all 94 endpoints, generated straight from the OpenAPI spec into MCP tools. Every tool is safety-categorized (🟢 read-only / 🟡 write / 🔴 destructive) so your assistant knows what an action does before it calls it. It runs over stdio (Claude Desktop and other local launchers) or Streamable HTTP (hosted in Docker), and ships with retries, client-side rate limiting, and request timeouts so it holds up against a live school.

Why you'll want this

Some MCP servers just forward an API. This one is built to be safe to hand to an LLM and easy to run for real:

How it compares

At the time of writing this appears to be the only dedicated LearnWorlds MCP server. You could instead point a generic OpenAPI→MCP wrapper at the spec — here's what that leaves on the table:

_{*Generic OpenAPI→MCP wrappers turn any Swagger/OpenAPI spec into MCP tools. They can reach the same endpoints, but treat every operation identically — no safety categories, no resilience, no deployment story, and no guardrails tuned for live school data. "➖" = varies by tool / not guaranteed. Snapshot from July 2026.}

What you can do

Once it's connected, ask your assistant things like:

• "List the 10 most recent users who signed up this month."
• "Create a user for jane@example.com and enroll her in the 'Pro' bundle."
• "Show me this month's payments and total revenue."
• "Which users haven't completed the 'Onboarding' course yet?"
• "Create a 20%-off coupon for the annual subscription plan."
• "Pull completion analytics for our top 5 courses."

Tools are generated automatically from the API and grouped into 🟢 read-only, 🟡 write, and 🔴 destructive — so a well-behaved host can treat each group differently.

How it works

Claude / Cursor / any MCP client  ──MCP──►  this server  ──HTTPS──►  LearnWorlds API (your school)

The server parses the bundled OpenAPI spec into MCP tools (resolving $refs and guarding against recursive schemas), tags each with its safety category, and injects your bearer token and Lw-Client header on every outgoing request. Your credentials stay in the server's environment — the model never sees or handles them.

Requirements

• A LearnWorlds school with API access — an access token and a Client ID (admin → Settings → Integrations → Developers), plus your school's API base URL. See Get your API credentials.
• Docker (Docker Desktop on macOS/Windows) for the quick start below — or Node.js ≥ 18 to run from source.

Quick start (Docker)

1. Add your credentials. Copy the example config and fill it in:

cp .env.example .env
# edit .env → set LEARNWORLDS_BASE_URL, LEARNWORLDS_API_TOKEN, LEARNWORLDS_CLIENT_ID
#           → set MCP_SHARED_TOKEN to a long random string if reachable beyond localhost

2. Start the server:

docker compose up -d --build

The bundled docker-compose.yml binds to 127.0.0.1:8765 only, so the server is reachable from your machine but not the network.

3. Confirm it's running:

curl -s http://localhost:8765/health
# → {"status":"ok","server":"learnworlds-mcp","tools":94}

4. Connect your MCP client. The MCP endpoint is http://localhost:8765/mcp.

• Claude Desktop — add a custom connector (Settings → Connectors) pointing at the URL, or bridge it locally with mcp-remote. Add this under mcpServers in your config, then fully quit and reopen the app:

  {
    "mcpServers": {
      "learnworlds": {
        "command": "npx",
        "args": [
          "mcp-remote",
          "http://localhost:8765/mcp",
          "--header", "Authorization: Bearer YOUR_MCP_SHARED_TOKEN"
        ]
      }
    }
  }
  

  (Drop the --header line if you left MCP_SHARED_TOKEN empty.)

• Claude Code — one command:

  claude mcp add --transport http learnworlds http://localhost:8765/mcp
  

• Claude Cowork — shares Claude Code's MCP config, so the command above makes the tools available there too.

Prefer a prebuilt image?

Every push to main publishes a ready-to-run image to the GitHub Container Registry, so you can skip the local build entirely:

docker run -d --name learnworlds-mcp -p 127.0.0.1:8765:8765 --env-file .env \
  ghcr.io/ohneben/learnworlds-mcp:latest

Find it in a registry

The server publishes itself to the official MCP Registry as io.github.ohneben/learnworlds-mcp, so MCP clients that browse the registry can install it without cloning anything:

curl "https://registry.modelcontextprotocol.io/v0/servers?search=io.github.ohneben/learnworlds-mcp"

server.json holds the registry metadata and glama.json the Glama directory entry.

Releasing is driven by the version in server.json: when a build sees a version the registry does not yet list, it tags the image with that version and publishes it, using GitHub OIDC so there is no token to store. Anything else — an ordinary push, a re-run, a second event for the same ref — leaves the released image tag and the registry entry untouched. Bumping the version is therefore the whole release: pushing a matching v* tag or running the workflow by hand still works and takes the same path, and a tag that disagrees with server.json fails the build rather than publishing the wrong thing.

The io.modelcontextprotocol.server.name label in the Dockerfile is what proves the image belongs to that name, so keep it in step with name in server.json. It is applied at build time — there is nothing to verify by hand.

Get your API credentials

1. Log in to your LearnWorlds school admin.
2. Go to Settings → Integrations → Developers (the API screen).
3. Copy your Access Token → LEARNWORLDS_API_TOKEN, and your Client ID → LEARNWORLDS_CLIENT_ID.
4. Set LEARNWORLDS_BASE_URL to your school's API base: https://<your-school>.learnworlds.com/admin/api. If your school uses a custom domain, use that host instead (e.g. https://academy.example.com/admin/api).

Put all three in .env. The server injects them on every request, so your assistant never sees them.

Configuration

Everything is set in .env (copied from .env.example):

After changing .env, reload with docker compose up -d --force-recreate.

Tool safety categories

Each tool's description starts with one of these banners and carries the matching MCP annotations:

The 🟡 write tools total 27 (17 create + 10 update). Hosts that respect annotations (Claude included) can require confirmation for destructiveHint tools and trust readOnlyHint tools automatically.

Under the banner, every description follows the same layout so an agent can act on the first read instead of probing:

Run npm run list-tools (no credentials needed) to print the full catalog and the per-category counts at any time.

Coverage by area (read / write / delete)

Area	🟢 Read	🟡 Write	🔴 Delete
Users	10	7	1
Affiliates	7	1	0
Community	6	3	2
Courses	5	3	0
Promotions (coupons)	4	3	0
Reporting	4	0	0
Payments	3	0	0
Multiple seats	3	3	2
User groups	3	3	2
Bundles	2	0	0
Assessments	2	1	0
Subscription plans	2	0	0
Certificates	1	1	1
User subscriptions	1	0	0
User roles	1	0	0
Installments	1	0	0
Leads	1	0	0
Calendar	1	0	0
Event logs	1	0	0
Asynchronous actions	1	0	0
Update user progress	0	2	0
Total	59	27	8

Run from source (stdio, no Docker)

Prefer the classic stdio mode for Claude Desktop? Build it locally:

npm install
npm run build

Then point Claude Desktop at the compiled entrypoint in claude_desktop_config.json:

{
  "mcpServers": {
    "learnworlds": {
      "command": "node",
      "args": ["/ABSOLUTE/PATH/Learnworlds-MCP/dist/index.js"],
      "env": {
        "MCP_TRANSPORT": "stdio",
        "LEARNWORLDS_BASE_URL": "https://your-school.learnworlds.com/admin/api",
        "LEARNWORLDS_API_TOKEN": "your-access-token",
        "LEARNWORLDS_CLIENT_ID": "your-client-id"
      }
    }
  }
}

Keeping the spec current

The bundled spec/learnworlds-openapi.yaml is the source of truth for the tools. To refresh against a newer API version, drop the new YAML in its place (or point LEARNWORLDS_OPENAPI_PATH at it) and rebuild:

docker compose up -d --build   # Docker
# or
npm run build                  # from source

New paths become new tools automatically — no code changes needed.

Development

npm install
npm run build      # compile TypeScript → dist/
npm test           # run the Vitest suite
npm run list-tools # print the categorized tool catalog (no credentials needed)

CI builds and tests every push across Node 20 and 22; pushes to main also publish a Docker image to the GitHub Container Registry. When the version in server.json is one the official MCP Registry does not yet list, that same run also publishes it there.

Notes & conventions

• Transports: MCP_TRANSPORT=stdio (default) for local launchers; MCP_TRANSPORT=http for the always-on Streamable-HTTP server the Docker image runs.
• Paging: most get tools accept page (and endpoint-specific filters); LearnWorlds paginates list responses (commonly 20–50 items per page).
• Rate limit: LearnWorlds allows 30 requests / 10 s; the server self-throttles at LEARNWORLDS_MAX_REQUESTS per LEARNWORLDS_RATE_WINDOW_MS (default 25 / 10 s) and retries any 429 it still receives.
• Request bodies: write tools take a body argument; its schema is resolved from the spec and shown to the model.

Security

• Your API credentials live only in .env, which is git-ignored. Never commit real secrets. If the token leaks, rotate it in LearnWorlds admin → Settings → Integrations → Developers (API).
• The HTTP endpoint is unauthenticated by default (fine on localhost). To expose it beyond your machine, set MCP_SHARED_TOKEN and send it as an Authorization: Bearer <token> header — ideally behind TLS.

See SECURITY.md for the full policy and how to report a vulnerability.

Credits & license

An unofficial community integration for LearnWorlds; not affiliated with or endorsed by LearnWorlds. Built on the Model Context Protocol. Licensed under the MIT License.