Kirana Khata
Drafts polite Hinglish payment reminder messages for WhatsApp and provides a WhatsApp link/chooser so the shopkeeper can decide whether to send them.
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., "@Kirana KhataRamesh ke naam 200 ka udhaar likho"
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.
🧾 Kirana Khata – a voice ledger for India's kirana shops
Shopkeepers have busy hands, so they keep the udhaar (credit) ledger in their head or on scraps of paper. Kirana Khata lets them just talk to Alexa+ in Hinglish:
"Ramesh ke naam 200 ka udhaar likho" → writes credit in Ramesh's name
"Sharma ji ne 500 diye" → records a payment
"Aaj kitna udhaar baaki hai?" → total pending
"Sabse zyada paisa kis se lena hai?" → biggest dues
"Pappu ko reminder bhejo" → drafts a polite Hinglish WhatsApp reminder
Track: Alexa+ (self-hosted MCP server) · Mini challenge: Open Source
How it works
server.py– a self-hosted MCP server (official Python MCP SDK, Streamable HTTP, protocol2025-11-25) at/mcpexposing 6 tools:add_udhaar,record_payment,get_balance,top_defaulters,draft_reminder,add_alias(nicknames like "chhota bhaiya" or "doodh wali didi" map to the right customer).db.py– SQLite ledger (no external API, no API key needed).static/index.html– shop dashboard + Alexa+ simulator (type or speak Hinglish; uses browser speech APIs).hinglish.py– small rule-based Hinglish parser used only by the simulator. Real Alexa+ understands the language itself and calls the MCP tools directly.test_mcp_client.py– a real MCP client that connects over Streamable HTTP and calls every tool (proof the MCP layer is used at runtime).
Related MCP server: voiceledger-mcp
Run it (Python 3.10+)
python -m venv venv
# Windows: venv\Scripts\activate Mac/Linux: source venv/bin/activate
pip install -r requirements.txt
python seed.py # demo data (made-up names)
python server.py # dashboard: http://127.0.0.1:8000 MCP: http://127.0.0.1:8000/mcpVerify the MCP server (in a second terminal): python test_mcp_client.py
To connect it to Alexa+ / any MCP client, expose /mcp over HTTPS (e.g. a tunnel or any host) and register that URL.
Limits (honest notes)
Demo data is synthetic. Not a replacement for proper accounting/GST software.
The simulator's Hinglish parser is rule-based and handles a fixed set of phrasings.
Reminders are drafts: the shopkeeper decides whether to send them (WhatsApp link opens the chooser).
License
MIT – see LICENSE.
This server cannot be deployed
Maintenance
Related MCP Connectors
AI for Tally Prime and Tally ERP 9. Hosted MCP server to ask your accounts in any language.
Personal finance ledger for AI agents — query spending, track bills, forecast cash flow.
Create invoices from your AI assistant in 6 languages and 10 currencies, ready for WhatsApp.
Run a lawn, pool or cleaning business by chat: today's route, visits, payments, who owes you.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables personal finance management through conversational AI, including expense tracking, budget monitoring, financial news simplification, and purchasing power comparisons across South Asian cities. Designed for WhatsApp integration with natural language commands for financial assistance.-
- AlicenseNot gradedqualityCmaintenanceEnables assistants to answer spoken questions about a cash trader's sales, expenses, stock levels, and outstanding debts from an append-only ledger, with deterministic figures for speech.MIT
- AlicenseNot gradedqualityBmaintenanceEnables users to log expenses and income by voice, auto-categorize transactions, set and check budgets, summarize spending, undo or search entries, and generate AI spending insights with an offline fallback.MIT
- AlicenseNot gradedqualityBmaintenanceEnables small shopkeepers to record credit and payment entries, check balances, list dues, and get ranked collection plans with drafted reminders through natural voice commands, including code-mixed Tamil/Hindi/English speech. It returns short spoken-style responses over a self-hosted Streamable HTTP MCP server backed by Amazon Bedrock, with a regex fallback when Bedrock is unavailable.MIT