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: Google Tasks 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.
Official Akiflow MCP for tasks, calendars, scheduling, time slots, and meeting transcripts.
Manage Superlist tasks and lists in plain language from any MCP-compatible AI agent.
Governed memory and workspace for any AI: tasks, calendar, mail and pages, with per-action consent.