BeeMind MCP Server
Provides Amazon Bedrock-powered semantic memory recall and agent orchestration over Amazon Bee wearable context, including device status, diarized transcripts, action items, and task dispatch.
Provides wearable context and tools for Apple Watch running Bee software, including device status, diarized transcripts, semantic memory search, and action items.
Enables syncing extracted meeting commitments and action items to Jira.
Enables syncing extracted meeting commitments and action items to Notion.
Enables syncing extracted meeting commitments and action items to Slack.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
π BeeMind: An Ambient AI Agent for Amazon Bee
Technical Subtitle
Proactive Memory, Commitment Tracking & MCP-Powered Tool Orchestration with Amazon Bedrock
Built for the Build, Ship, Shape: Amazon Developer Hackathon 2026
Targeting the Bee (Wearable AI) Track, AWS Builder Mini Challenge, and Open Source Mini Challenge.
π Overview
BeeMind is an ambient intelligence companion and open Model Context Protocol (MCP) server designed for the Amazon Bee Wearable ecosystem (Bee Frontier, Bee Eclipse, and Apple Watch running Bee software).
By converting continuous acoustic streams into actionable intelligence without storing raw audio, BeeMind powers:
π§ Proactive Second Brain & Recall: Semantic Q&A over daily memories and recommendations using Amazon Bedrock embeddings.
π€ Real-Time Meeting Commitments: Instant extraction of action items, assignees, and deadlines, syncing to Jira, Notion, and Slack.
π· Hands-Free Field & Industrial Workflow: Voice-checked audit reports, vibration/pressure telemetry, and hazard alerts for deskless workers.
β‘ Ambient Agentic Bridge & Bee MCP Server: Open Model Context Protocol (MCP) server enabling external AI agents (Claude, Bedrock AgentCore) to interact with wearable context.
Related MCP server: Nouva MCP Server
ποΈ Architecture
ββββββββββββββββββββββββββββββββββββββββββ
β Amazon Bee Wearable / Apple Watch β
β (Acoustic Diarization & Telemetry) β
βββββββββββββββββββββ¬βββββββββββββββββββββ
β
Bee CLI / REST Ingestion Endpoint
β
βΌ
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β BeeMind Ambient Core Engine β
β β
β ββββββββββββββββββββββββββ ββββββββββββββββββββββββββ β
β β Amazon Bedrock β β Model Context β β
β β Runtime Service β β Protocol (MCP) β β
β β (Claude 3.5 Sonnet / ββββββββββββββββββββΊβ stdio Server β β
β β Nova / Titan) β β (5 Active Tools) β β
β ββββββββββββββββββββββββββ ββββββββββββββββββββββββββ β
ββββββββββββββββββββββββββββββββββββββββ¬βββββββββββββββββββββββββββββββββββββββ
β
βΌ
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β BeeMind Interactive Companion UI β
β β
β [Live Audio Stream] [Second Brain] [Action Items] [Field Mode] β
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββπ Quickstart & Setup
Prerequisites
Node.js 18+ (tested on Node.js v24)
npm or pnpm
1. Clone & Install
git clone <your-repo-url>
cd Amazon
npm install2. Environment Variables (Optional)
Copy .env.example to .env.local:
cp .env.example .env.localNote for Judges: If AWS credentials are not set, BeeMind runs automatically with its Intelligent Zero-Config Local Engine so you can evaluate all features immediately!
3. Run the Development Server
npm run devOpen http://localhost:3000 in your browser.
4. Run the Model Context Protocol (MCP) Server
To connect BeeMind to Claude Desktop, Cursor, or any MCP-compatible agent client:
npm run mcp:runMCP Configuration snippet (claude_desktop_config.json):
{
"mcpServers": {
"beemind-wearable": {
"command": "npx",
"args": ["tsx", "server/mcp/index.ts"],
"cwd": "/path/to/project"
}
}
}5. Run the Bee Wearable Stream Simulator
Simulate real-time streaming audio events into the companion dashboard:
npm run simulate:beeπ οΈ MCP Tools Reference
The BeeMind MCP server exposes 5 standardized tools:
MCP Tool Name | Description | Parameters |
| Returns wearable battery level, connection, and recording mode | None |
| Returns the latest diarized spoken transcripts with confidence |
|
| Semantic RAG query across user's wearable memory |
|
| Retrieves extracted commitments and assigned tasks |
|
| Dispatches autonomous agent workflows from spoken intent |
|
π Repository Structure
βββ app/
β βββ api/
β β βββ bedrock/chat/route.ts # Natural language memory recall
β β βββ bedrock/status/route.ts # Device & AI engine status
β β βββ bee/stream/route.ts # Audio chunk ingestion
β βββ globals.css # Glassmorphism & audio waveform styles
β βββ layout.tsx # Root layout with BeeMind branding
β βββ page.tsx # Crextio luxury bento companion app
βββ lib/
β βββ bedrock-service.ts # AWS Bedrock + Zero-Config fallback engine
β βββ bee-store.ts # Seed data & store definitions
β βββ types.ts # TypeScript models
βββ public/
β βββ logo.png # Official BeeMind cybernetic logo
βββ server/
β βββ bee-simulator.ts # CLI stream generator
β βββ mcp/index.ts # Official Model Context Protocol Server
βββ AMAZON_FEEDBACK.md # Feedback for Amazon Bee Developer team
βββ DEMO_SCRIPT.md # 3-minute video pitch script
βββ DEVPOST_SUBMISSION.md # Devpost text ready to submit
βββ LICENSE # Open source MIT license
βββ package.jsonπ License
Released under the MIT License.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
This server cannot be deployed
Maintenance
Related MCP Connectors
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
Agent-native notes, tasks, dev-docs, vaults, sync & handoffs. MCP + OpenAPI dual surface.
Persistent personal memory for AI assistants β save, search, and recall across every MCP client.
Governed personal world model and memory for your AI agent. Pair once, connect over MCP.
Related MCP Servers
AlicenseAqualityCmaintenanceEnables AI assistants to query end-to-end encrypted memories from Cognia workspace via MCP. Supports search, retrieval, and action execution against connected services like Slack, Notion, and GitHub.56 npmMIT- FlicenseNot gradedqualityBmaintenanceEnables AI agents to maintain persistent personal memory and portable skills across MCP-compliant clients, with hybrid semantic recall and deterministic SQL analytics.-
- AlicenseNot gradedqualityCmaintenanceEnables MCP clients to discover and create agents, durably submit messages with verifiable replies, and search source-linked local memory. Exposes eight authenticated tools with owner-approved OAuth, transcript-backed verification, and explicit control over history import and embedding.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to query your complete local conversation history and knowledge graph over MCP, including full-fidelity transcripts, search, and typed, dated entity relationships.AGPL 3.0