Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Moodle MCP Server list my courses for this semester"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Servidor MCP (Model Context Protocol) para exponer tools que permiten a un LLM interactuar con Moodle mediante su API REST.
Estado: baseline listo para producción ligera (TypeScript + Fastify). Incluye validación con Zod, logging con Pino, estructura de acciones y cliente REST con backoff.
Node.js 20+
Token de servicio en Moodle (REST)
URL base de Moodle (p. ej. https://elearning.org)
Related MCP server: moodle-mcp
Copia .env.example a .env y ajusta valores:
MOODLE_BASE_URL=https://elearning.example.org
MOODLE_TOKEN=xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
MOODLE_FORMAT=json
PORT=7410
LOG_LEVEL=infoInstala dependencias:
npm installArranca en modo desarrollo:
npm run devEl servidor expone:
GET /health → ok
POST /mcp/tools → invocar tools MCP con payload { tool, arguments }
GET /mcp/resources/:type/:id → recursos cacheables (course, user, assignment)
Listar cursos:
curl -X POST http://localhost:7410/mcp/tools -H "content-type: application/json" -d '{"tool":"list_courses","arguments":{"search":"prospectiva","limit":10}}'Buscar usuario por email:
curl -X POST http://localhost:7410/mcp/tools -H "content-type: application/json" -d '{"tool":"get_user_by_email","arguments":{"email":"alguien@org.org"}}'Matricular usuario:
curl -X POST http://localhost:7410/mcp/tools -H "content-type: application/json" -d '{"tool":"enroll_user","arguments":{"userid":123,"courseid":456,"roleid":5}}'src/
index.ts # bootstrap Fastify
mcpServer.ts # registro y ruteo de tools/resources
moodleClient.ts # wrapper REST Moodle con backoff
config.ts # carga de env
utils/
validators.ts # esquemas Zod
error.ts # tipos/ayudantes de error
logging.ts # logger Pino
actions/ # handlers MCP
courses.ts
users.ts
enrollments.ts
assignments.ts
forums.ts
files.ts
quizzes.ts
schemas/ # (espacio para JSON Schemas si los separas)
test/
params.test.ts # tests de flatten/validación
mcp.json # manifest MCPEndpoint: {MOODLE_BASE_URL}/webservice/rest/server.php
Parámetros obligatorios: wstoken, wsfunction, moodlewsrestformat
Codificación de arrays: courseids[0]=123&courseids[1]=456 (ya soportado por flattenParams).
Errores: el cliente normaliza errores HTTP/REST y texto de Moodle.
docker build -t moodle-mcp .
docker run --env-file .env -p 7410:7410 moodle-mcpMIT © 2025
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Official Microsoft MCP Server to query Microsoft Entra data using natural language
Manage SRG+ hubs, channels, content, assets, users, and workspaces from any MCP-aware AI agent.
Connect AI assistants to Stellary projects, boards, documents, and governed agent workflows.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/cfsandoval/mcpmoo'
If you have feedback or need assistance with the MCP directory API, please join our Discord server