PantryPilot MCP Server
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., "@PantryPilot MCP ServerWhat can I make for dinner using only what's in my pantry?"
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.
PantryPilot — Alexa+ Experience
PantryPilot is a polished, browser-based simulation of a brand experience for Alexa+. A customer asks for a weeknight dinner, Alexa+ coordinates brand tools, and the customer can tune servings or approve missing ingredients without leaving the conversation.
Live demo: pantrypilot-alexa-plus.vercel.app
This submission follows the “new to MCP” path in the project brief: it is a self-contained simulated experience, not a production Alexa integration. The interaction model is informed by the MCP Apps Agent Skills guide: structured tools drive the same state as the visible interface, tool activity is transparent, and consequential actions require explicit confirmation.
What the demo shows
A realistic Alexa+ request-to-result conversation
A visual dinner recommendation based on pantry, diet, and time constraints
Adjustable servings with live ingredient scaling
Three selectable pantry-first meal options
An approval-gated shopping list with removable items and feedback
A guided cooking mode with step progress and working timers
Conversational and one-tap plan refinements
A live brand-tool trace for
read_pantry,find_recipe, andbuild_cartAn inspectable JSON result with a clear
purchaseMade: falseboundaryResponsive desktop and mobile layouts
Browser-native WebMCP tools that agents can discover and call
A production-hosted Streamable HTTP MCP endpoint at
/mcp
Related MCP server: Gamito
Run locally
Requirements: Node.js 22.13 or newer and npm.
npm install
npm run devOpen http://localhost:5173.
Create a production build with:
npm run buildThe repository is a standard Next.js project and can be imported directly into Vercel with no environment variables.
Streamable HTTP MCP server
The same Vercel deployment hosts a stateless MCP server at:
https://pantrypilot-alexa-plus.vercel.app/mcpIt uses the official MCP TypeScript SDK, negotiates protocol version 2025-11-25, supports Streamable HTTP POST requests and optional GET streams, validates browser Origin headers, and scales safely across serverless instances. No API key is required because the server exposes only simulated demo data.
Server-side capabilities:
Capability | Purpose |
| Read the simulated household pantry |
| Rank pantry-first recipes by time and preferences |
| Read a complete guided-cooking plan |
| Stage missing ingredients after |
| Read the pantry as an MCP resource |
Test protocol negotiation:
curl https://pantrypilot-alexa-plus.vercel.app/mcp \
-H 'Content-Type: application/json' \
-H 'Accept: application/json, text/event-stream' \
--data '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-11-25","capabilities":{},"clientInfo":{"name":"curl","version":"1.0.0"}}}'Agent-facing tools
Browsers that support the proposed imperative WebMCP interface can discover five page-scoped tools:
Tool | Purpose | Side effect |
| Read the visible recipe, time, servings, and missing-item count | None |
| Select one of the three visible recipe options | Updates the active meal |
| Set servings from 1–12 | Updates the visible recipe card and ingredient quantities |
| Add missing ingredients after | Updates the simulated list; never purchases |
| Open the selected meal at step one | Opens the visible guided-cooking dialog |
Each tool validates its input and updates the same React state as the on-screen controls. Unsupported browsers simply ignore the optional registration and the visual demo continues to work.
Interaction checklist
Switch among the three meal options or use a quick refinement.
Use the plus/minus controls to scale servings and ingredients.
Add missing items, then remove individual items from the list if needed.
Open Start guided cooking and move through the recipe steps or run a timer.
Open Inspect result to see the structured response data.
Project structure
app/
page.tsx Experience UI, state, and WebMCP registrations
globals.css Responsive visual system and interaction states
layout.tsx Page metadata and document shell
public/
grain-bowl.jpg Optimized original recipe photography
favicon.svg PantryPilot markThe project uses Next.js 16, React 19, TypeScript, Tailwind CSS 4, and Lucide icons. It requires no API key, database, account, or external service.
Accessibility and trust
Semantic landmarks and useful accessible names
Visible keyboard focus states
Reduced-motion support
Responsive behavior down to mobile widths
No purchase, checkout, or external transmission in the simulation
Explicit confirmation before updating the shopping list
From simulation to production
For a production Alexa+ submission, replace the in-page simulated tools with a self-hosted Streamable HTTP MCP server using specification 2025-11-25 or later, preserve the same tool boundaries, add authentication and durable household state, and test with the current Alexa+ developer preview requirements.
Asset note
The food photograph was generated specifically for this project. No external runtime assets are fetched.
This server cannot be deployed
Maintenance
Related MCP Connectors
Household-aware cooking brain: pantry, meal suggestions, dietary safety, recipes, 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-powered kitchen management — pantry, recipes, meal plans, shopping lists
AI meal plans that fill your Kroger/Instacart cart - pantry-aware lists, all from chat.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceHousehold-aware kitchen brain for AI agents: manage pantry inventory with freshness tracking, shopping lists, recipe collections with cook notes and per-diner ratings, dietary profiles with allergen safety, and kitchen equipment — all through 27 tools with OAuth 2.1 authentication. Includes a free tool for ingredient-based recipe generation without an account (accounts are free!).MIT
- FlicenseBqualityDmaintenanceEnables AI agents to generate budget-disciplined, allergy-safe weekly meal plans, shopping lists, and meal swaps using a fully local deterministic engine.20-
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to read current pantry inventory and low-stock shopping needs, export a shopping queue, and perform idempotent inventory adjustments and catalog link management through remote MCP tools.MIT
- FlicenseNot gradedqualityBmaintenanceEnables MCP-compatible clients like ChatGPT and Claude to manage a household's shared food inventory, meal plans, recipes, and preferences through natural language, with atomic updates and audit logging.-