Skip to main content
Glama

Alexa+ MCP: skills-driven smart-home agent

A self-hosted MCP server (spec 2025-11-25, Streamable HTTP) with Agent Skills (skills/*/SKILL.md, exposed as MCP resources) and a web app that simulates the Alexa+ experience. An optional Amazon Bedrock agent discovers tools and skills over MCP and calls them.

Run

npm install
npm start                      # http://127.0.0.1:3000  (MCP endpoint: /mcp)

Optional LLM agent (AWS Builder mini challenge):

export AWS_REGION=us-east-1 BEDROCK_MODEL_ID=<model or inference-profile id you have access to>
npm start

Without these variables the web app falls back to a rule-based planner (still calling real MCP tools).

Related MCP server: smarthome-mcp

Test the transport

curl -i -X POST http://127.0.0.1:3000/mcp -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-11-25","capabilities":{},"clientInfo":{"name":"curl","version":"1"}}}'

Check that result.protocolVersion is 2025-11-25 and an Mcp-Session-Id header is returned. If it is older, update @modelcontextprotocol/sdk. Or run npx @modelcontextprotocol/inspector and connect to http://127.0.0.1:3000/mcp.

Layout

src/server.js MCP server and routes · src/agent.js Bedrock agent loop · skills/ Agent Skills · public/index.html web client

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables MCP-compatible AI agents to read room temperatures and control smart home lights via natural language.
    1
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    An 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
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables a voice assistant to operate a local agent fleet over MCP Streamable HTTP, allowing users to dispatch missions, monitor parallel worker execution, and collect reports hands-free.
    MIT