Munim MCP Server
Integrates Munim with Amazon Alexa+, exposing restaurant operations through voice-first MCP tools for shop briefs, cited business questions, pending approvals, and customer storefront availability.
Provides a code-only AWS identity adapter for Amazon Cognito user pools, including ID-token verification via JWKS and password-grant authentication. Not deployed in the live demo.
Provides a code-only AWS blob-storage adapter using Amazon S3 as the storage backend. Not deployed in the live demo.
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., "@Munim MCP ServerWhich ingredients are running low at Hazratganj?"
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.
Munim on Alexa+
Ask your restaurant's books out loud and get answers you can trust. Munim is an operating system for small restaurant groups, bakeries and cloud kitchens: till, kitchen, stock, purchasing and ledgers, with AI specialists that explain what happened, find money leaking, and draft actions. A person approves every change.
This repo puts Munim behind Alexa+ as a self-hosted MCP server (Streamable HTTP, spec 2025-11-25) plus an Agent Skill, with a simulated Echo Show client. Alexa+ can already reorder a meal from a delivery app. What it can't do is answer "which ingredients are running low at Hazratganj?" from your own stock records, with every number cited, or say "Cannot verify" instead of guessing. It also can't take the owner's yes or no on a proposal. This repo adds those.
Live, inside the Cobnut Bakehouse website: https://munim-cobnut-alexa.vercel.app/alexa · MCP endpoint
https://munim-cobnut-alexa.vercel.app/mcp(seecobnut-integration/)Standalone: https://munim-alexa.vercel.app (Echo Show simulator) · MCP endpoint
https://munim-alexa.vercel.app/mcpDemo business: Cobnut Bakehouse, a synthetic two-outlet bakery in Lucknow running on the live Munim deployment. All data is synthetic.
Tools
Tool | Who | What |
| owner | open findings (waste spikes, lapsing regulars, licences), how many are high, approvals waiting |
| owner | any question about the business. Munim's specialists answer only from the books: every number is a |
| owner | the proposals Munim drafted (campaigns, purchase orders, recipe changes), numbered |
| owner | the owner's decision, recorded through Munim's guarded approval command ( |
| customer | from the live storefront (public storefront key) |
Every result carries a ready-to-speak speech sentence plus structured data for Echo Show cards.
Related MCP server: agent-storefront
How it works
Echo Show sim (browser MCP client) ─┐
Claude / any MCP client ─┼─ JSON-RPC over Streamable HTTP ─▶ api/mcp.js (Vercel function, stateless)
┘ │ lib/munim.js
├─ owner lane: Cobnut demo sign-in → Bearer + X-Munim-Tenant
└─ customer lane: X-Munim-Storefront-Key
▼
Munim core API (munim-api.vercel.app) → Postgres, AI specialistsapi/mcp.js:McpServer+StreamableHTTPServerTransport(TS SDK 1.32.1,LATEST_PROTOCOL_VERSION2025-11-25), stateless with JSON responses, one server per request.lib/munim.js: the API client, citation resolver (_minor→ ₹,_milli→ units,_bp→ %) and UUIDv7 command ids.public/index.html: the simulated Echo Show. It's a real MCP client: initialize → tools/list → tools/call. It takes Web Speech voice in/out, renders cards and shows the wire log. Owner and customer modes.skills/munim-owner/SKILL.md: the Agent Skill (intent → tool, citation and approval rules).
Run
npm install
MUNIM_STOREFRONT_KEY=… node scripts/local.mjs # http://localhost:3000 (page) + /mcp
node scripts/check.mjs https://munim-alexa.vercel.app/mcp # asserts protocolVersion 2025-11-25, lists tools, calls shop_brief
claude mcp add --transport http munim https://munim-alexa.vercel.app/mcp # or MCP InspectorEnv: MUNIM_STOREFRONT_KEY (required for customer tools), MUNIM_API_ORIGIN, MUNIM_WEB_ORIGIN (defaults: the live
Munim deployment).
Built during the hackathon
Munim itself (core API, AI specialists, storefront, Cobnut demo) existed before the hackathon. This repo (the MCP server, the citation resolver, the voice-first tool design, the Echo Show client and the Agent Skill) was built on 23 Oct 2026.
MIT licence.
AWS adapter (code only)
adapters/aws/ holds AWS counterparts of Munim's GCP cloud adapters: idp-cognito (Amazon Cognito user pools in place
of Identity Platform: ID-token verification against the pool's JWKS, plus the InitiateAuth password grant) and
blob-s3 (Amazon S3 in place of Cloud Storage for the blob port). Status: code only, not deployed — the live demo runs
on Supabase via the Munim (food-ops) deployment. Tests run offline: node --test 'adapters/aws/**/*.test.js'. See
adapters/aws/README.md.
This server cannot be deployed
Maintenance
Related MCP Connectors
- OpenAjanOAuthcom.openajan
Find local shops, read live menus and free times, and order or book on the user's behalf.
Per-restaurant MCP servers: menu, hours, delivery terms; live example below
- mcpOAuthcom.zomato
An MCP server that exposes functionalities to use Zomato's services.
Restaurant menus, carts, reservations and owner drafts for AI agents (Thmenu MCP).
Related MCP Servers
- FlicenseAqualityDmaintenanceAn MCP server for restaurant discovery and booking across Resy and OpenTable via natural language. It integrates Google Places data with dietary preferences, visit history, and weather awareness to provide personalized dining recommendations and group reservation management.23-
- FlicenseNot gradedqualityDmaintenanceEnables any AI agent to discover, query, and order from a restaurant's storefront via MCP tools. It handles menu lookup, modifier validation, and enforces a mandatory confirmation gate before payment, replacing the human-operated phone line.-
- FlicenseNot gradedqualityBmaintenanceEnables AI agents to query a restaurant's governed knowledge documents, including menu, allergen info, reservation and refund policies, and hours, over MCP.1-
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to search restaurants, publish and maintain store data, submit verified freshness feedback, and query demand or updates through MCP tools. It provides both read-only and full administrative endpoints backed by open restaurant data.1AGPL 3.0