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., "@todo-hud-mcp Set tasks: review PR, write docs"
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.
Backend POC + desktop UI for Focus HUD, a lightweight todo + gamified pomodoro app.
apps/api/ # NestJS backend (REST + MCP)
packages/shared/ # Shared contracts/types (future)
infra/docker/ # Docker Compose config
infra/caddy/ # Caddy reverse proxy config (future)
docs/adr/ # Architecture Decision RecordsRelated MCP server: MCP Todo List
cd apps/api
npm install
npm run build
npm startServer at http://localhost:3000. Swagger at /docs.
docker compose up -d --buildHTTP: POST /mcp (inside NestJS)
Stdio: cd apps/api && npm run mcp
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server exposing the Backtest360 engine API as tools for AI agents.
Hosted MCP server for personal tools: budgets, savings goals, spaced repetition, tips, countdowns.
MCP server for generating rough-draft project plans from natural-language prompts.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/FelipeDanielH/todo-hud-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server