Click on "Deploy 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., "@AlexaTasker add a task to call the dentist tomorrow"
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.
An MCP (Model Context Protocol) server that bridges Alexa+ to a real task and calendar assistant — powered by AWS Bedrock for AI-generated daily planning.
Built for the Fire TV / Alexa+ / Ring / Bee Hackathon — Alexa+ track + AWS Builder mini.
AlexaTasker exposes a set of tools over MCP (Streamable HTTP, spec 2025-11-25+) that let an Alexa+ agent manage your tasks conversationally:
add_task — add a new task, optionally with a due date
list_tasks — list current (or completed) tasks
complete_task — mark a task as done
plan_day — ask AWS Bedrock (Claude) to generate a time-blocked plan for your day based on your current task list
The idea: instead of manually opening a to-do app, you just tell Alexa+ "add a task to call the dentist tomorrow" or "plan my day," and AlexaTasker handles the logic behind the scenes.
Related MCP server: Todoist MCP Server
Node.js + TypeScript
Express
@modelcontextprotocol/sdk (Streamable HTTP transport)
AWS Bedrock (@aws-sdk/client-bedrock-runtime)
Zod for schema validation
Node.js 20+
An AWS account with Bedrock model access enabled
AWS IAM credentials scoped to Bedrock (bedrock:InvokeModel)
Clone the repo:
git clone https://github.com/YOUR_USERNAME/taskbridge-mcp.git
cd alexatasker-mcpThis server cannot be deployed
Manage tasks, Focus Zone, notes, projects, and task history from compatible AI assistants.
Manage Superlist tasks and lists in plain language from any MCP-compatible AI agent.
Read tasks, habits, events and scheduling links; create and update Reclaim tasks and habits.
AI teammate for tasks: builds your list from meetings, email and chats, and checks off done work.
