Skip to main content
Glama
dustingibson-jpg

Alexa+ AWS Bedrock Orchestrator MCP

by dustingibson-jpg
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Alexa+ AWS Bedrock Orchestrator MCP

Python Test Suite License: MIT MCP Spec

An enterprise-grade, open-source Streamable HTTP Model Context Protocol (MCP 2025-11-25) server integrating Alexa+ voice intents with AWS Bedrock (anthropic.claude-3-5-sonnet) for multi-surface device orchestration across Ring, Fire TV, and Wearable AI.

Key Features

  • Full MCP Protocol Compliance: Implements MCP 2025-11-25 JSON-RPC transport via FastAPI (initialize, tools/list, tools/call, prompts/list, prompts/get, resources/list, resources/read).

  • AWS Bedrock Orchestration: Uses boto3 to stream user prompts through Anthropic Claude 3.5 Sonnet on AWS Bedrock for intent evaluation and multi-step reasoning.

  • Multi-Surface Coordination: Triggers contextual ambient actions across Ring doorbells, Fire TV video streams, and Wearable AI haptic sync.

  • Embedded Web Simulator: Serves an interactive simulator UI at http://localhost:8000 to visualize JSON-RPC request and response payloads in real time.

  • CORS & Inspection Ready: Configured with CORS middleware for compatibility with external MCP inspector tools.

  • Automated CI/CD: Verified with pytest unit testing and GitHub Actions workflow on every push.

Related MCP server: JudgeGuard

MCP Capabilities Schema

Tools

  1. query_bedrock_agent: Evaluates intent and executes agentic reasoning on AWS Bedrock.

  2. get_device_status: Fetches telemetry from Ring, Fire TV, or Wearables.

  3. execute_ambient_action: Executes multi-device actions (e.g., displaying camera feed on Fire TV).

Prompts

  1. smart_home_routine_assistant: Template for multi-device ambient automation.

  2. security_sweep_audit: System prompt for automated Ring/Fire TV security checks.

Resources

  1. ambient://device_logs: Real-time telemetry event stream.

  2. ambient://session_summary: Multi-turn conversational session context.

Quickstart

Prerequisites

  • Python 3.9+

  • AWS Credentials configured with Bedrock access (us-east-1 default)

Installation & Execution

# Clone repository
git clone [https://github.com/dustingibson-jpg/alexa-plus-bedrock-mcp.git](https://github.com/dustingibson-jpg/alexa-plus-bedrock-mcp.git)
cd alexa-plus-bedrock-mcp

# Install dependencies
pip install -r requirements.txt

# Run unit test suite
python3 -m pytest test_server.py

# Launch MCP Server & Web Simulator
python3 server.py

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Aura+

    tejas004s
    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

  • JudgeGuard

    kiza-zmaj
    A
    license
    Not graded
    quality
    B
    maintenance
    Enables autonomous AI governance and pre-action verification for Alexa+ agents, blocking high-risk operations like unlocking doors or financial transactions while grounding decisions in verifiable policy and AWS Bedrock reasoning.
    MIT

  • Aura+

    Sidopolis
    A
    license
    Not graded
    quality
    B
    maintenance
    Enables an Alexa-style assistant to plan and execute multi-step smart home routines, remember user preferences across sessions, and render interactive UI cards on screen via Streamable HTTP MCP tools. Uses AWS Bedrock for reasoning with a built-in offline intent fallback.
    MIT