HomeBrain
Provides integration with Amazon Alexa+, enabling household operations such as tracking what the home owns and what is covered, as well as running multi-turn repair cases that include troubleshooting, finding a provider, booking with passkey verification, and setting reminders.
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., "@HomeBrainThe water heater is leaking, can you start a service case?"
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.
HomeBrain
Alexa knows who is in the room. HomeBrain decides what that person is allowed to do.
HomeBrain is a self-hosted MCP server for Alexa+. It gives a household a durable brain for home operations. It knows what the household owns and what's covered, and it runs repair cases that last many turns and many days: troubleshooting, finding a provider, booking with passkey verification, and reminders.
Status: under construction for the Amazon "Build, Ship, Shape" hackathon (Alexa+ track). See DESIGN.md for the approved design and dated plan.
Honest labels
HomeBrain does not recognise voices. Alexa+ does that; an MCP tool call carries no audio.
The demo conversation is driven by an Alexa+ stand-in: Bedrock Claude driving the same MCP tools Alexa+ would call. It is not Alexa.
Service providers and bookings are demo fixtures (
data_source: "DEMO_FIXTURE").
Related MCP server: Alfred
Quick start (local)
make install # uv sync + pre-commit hooks
make check # lint, type-check, tests
make up # docker compose: server + DynamoDB Local
curl localhost:8080/healthzLicence
Apache-2.0. See LICENSE.
This server cannot be deployed
Maintenance
Related MCP Connectors
Private-by-default, local-first memory/context/task orchestrator for MCP apps and agents.
- EngramOAuthapp.getengram
Persistent, verbatim, searchable memory for AI assistants — one memory across every MCP client.
Cloud-hosted MCP server for durable AI memory
An MCP memory server. One memory your agents share — across models, devices and apps.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceA self-hosted MCP server that provides any LLM with a graph-backed memory layer of your life—tasks, email, finance, contacts, calendar—plus autonomous agent offices that act on your behalf.1Apache 2.0
- AlicenseBqualityAmaintenanceA local-first open-source MCP server that acts as a personal secretary, memory manager, and automation hub—it syncs Calendar, Gmail, Canvas, GitHub, and Health into a typed temporal memory graph, and enables approval-gated write actions like creating events, drafting/sending mail, and filing issues, all with telegram/slack/CLI interfaces and a SQLite-backed audit trail.33Apache 2.0
- AlicenseNot gradedqualityCmaintenanceGives Alexa+ persistent, structured memory of a household kitchen: tracking purchased groceries, flagging items at risk of spoiling, proposing rescue meals from expiring ingredients, and maintaining shopping lists, receipt ingestion, and waste reports through MCP tool calls. Storage, tool logic, and safety controls (consent gates, two-step deletion, rate limiting) are exposed over Streamable HTTP for any MCP client.MIT
- AlicenseNot gradedqualityBmaintenanceAn MCP server that enables Alexa+ to autonomously orchestrate multi-step household tasks by decomposing goals into parallel tool calls — cross-session memory and dietary/allergy auditing, culinary planning with wine pairings, Amazon Fresh cart assembly with human-in-the-loop purchase approval, smart-home ambiance and climate control, and calendar scheduling. It pairs AWS Bedrock multi-agent reasoning with Streamable HTTP transport and interactive generative UI cards, carousels, and live IoT sliders.MIT