Integrates with Amazon Alexa+ to provide a live household food inventory, expiry warnings, use-it-up meal suggestions, grocery list management, and kitchen statistics through voice or chat interactions.
Click on "Install 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., "@ShelfLife MCP what's expiring in my fridge this week?"
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 server that gives Alexa+ a live household food inventory — expiry warnings, use-it-up recipes, and grocery lists — built to end the "I forgot it was in the fridge" economy.
Track: Alexa+ (self-hosted MCP server, spec 2025-11-25, Streamable HTTP) · Mini-challenges: Open Source + AWS Builder
Built for the Build, Ship, Shape: Amazon Developer Hackathon.
node server/index.js # zero npm dependencies, Node 18+
→ MCP endpoint http://localhost:8931/mcp
→ Alexa+ sim http://localhost:8931/simulator/~1/3 of food produced is wasted, and a huge slice of household waste is simply food that expired unnoticed. Voice assistants already sit in the kitchen — but they can't see your pantry. ShelfLife fixes that: talk to it like Alexa, and it knows what you own, what's dying, and what to cook tonight.
Related MCP server: household-agent
Piece | What it is |
| Isomorphic MCP core: 9 tools (pantry CRUD, expiry radar, use-it-up meal suggestions, grocery list) + a JSON-RPC 2.0 / MCP message handler |
| Self-hosted MCP server — Streamable HTTP transport ( |
| Simulated Alexa+ experience — browser chat + voice (Web Speech API) that runs the same core through real |
| Optional AWS Builder integration: enriches |
The MCP server implements Streamable HTTP with protocol-version negotiation (2025-11-25 / 2025-06-18 / 2025-03-26), initialize, notifications/initialized, ping, tools/list, tools/call, and Mcp-Session-Id — see server/index.js:handlePostMcp().
Point any MCP client at it:
curl -X POST http://localhost:8931/mcp \
-H 'Content-Type: application/json' -H 'Accept: application/json, text/event-stream' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'The simulator is the "simulated Alexa+ experience" path done properly: it is not a mock — it executes the identical JSON-RPC handshake (initialize → notifications/initialized → tools/call) against the identical core the HTTP server serves.
pantry_add_item · pantry_list · pantry_check_expiry · pantry_remove_item · suggest_meals · grocery_add · grocery_list · grocery_remove · kitchen_stats
Explainable urgency: pantry_check_expiry ranks by real date math; suggest_meals scores recipes by how much expiring food they consume — no black box.
One core, two transports: the browser demo and the HTTP server cannot drift apart, because they literally share core/mcp-core.js.
Zero-dependency server: a pantry volunteer (or you) can run this on a potato. Persistence is a human-readable JSON file (data/pantry.json).
Open the simulator and try: "what's expiring?" → "what can I cook tonight?" → "I bought 2 kilos of chicken" → "add milk to the shopping list" → "kitchen summary". Flip to the protocol panel to watch each utterance become an MCP tools/call.
MIT — see LICENSE.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Household-aware cooking brain: pantry, meal suggestions, dietary safety, recipes, shopping lists.
AI-powered kitchen management — pantry, recipes, meal plans, shopping lists
Scraps Kitchen gives any AI agent a persistent, household-aware kitchen memory. Unlike generic chatbot recall, Scraps maintains structured cooking data: what's in your fridge (with freshness tracking), who you cook for (with allergens, dietary restrictions, and preferences), your recipe collection (with cook notes and per-diner ratings), your shopping list, and your kitchen equipment. 27 tools across 6 domains let agents read kitchen context, suggest meals that respect dietary safety, update the pantry after cooking, and build a history of what works for your household. Every interaction makes the data richer. Cooking history, preference signals, kitchen awareness = better suggestions next time. All tools work via oAuth and a free scraps.kitchen account.
AI meal plans that fill your Kroger/Instacart cart - pantry-aware lists, all from chat.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/renhongtao2-cell/shelflife-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
