mcp-starter-kit
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., "@mcp-starter-kit How much for 3 lattes and a pastry platter?"
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.
๐ The Plain-English MCP Starter Kit
Everyone's talking about "MCP." Here's one you can actually use โ in 5 minutes, with your own business.
You've probably heard that AI can now "connect to your tools." That connection has a name: MCP (Model Context Protocol). It's how an AI assistant stops guessing and starts answering with your real business data โ your hours, your prices, your FAQs.
This kit is a tiny, working MCP server. You edit one file with your info, run one command, and connect it to your AI. Then you can ask your AI things like:
"How much for 3 lattes and a pastry platter?" "What are your Saturday hours?" "What times are open this week?"
โฆand it answers correctly, every time โ because it's reading your data, not making it up.
๐ฌ Want the link to this kit? Comment "MCP" on the post and we'll send it over.
What's an MCP, in one sentence?
An MCP server is a safe translator between your AI and your stuff. The AI can only do the specific actions you allow โ nothing else on your computer.
See the picture: docs/diagram.md
This kit allows exactly four safe, read-only actions:
Action | What it does |
| Shares your hours, contact, and address |
| Calculates a price from your service list |
| Answers common customer questions |
| Lists your open booking slots |
Related MCP server: MCP Server Starter
Set it up in 5 minutes
You need: Node.js (the free "LTS" download) and a free AI app that supports MCP, like Claude Desktop. You do not need to know how to code.
1. Download this kit
Click the green Code button above โ Download ZIP โ unzip it.
2. Add your business info
Open business.json in any text editor and replace the example
(Maple Street Coffee) with your own name, hours, services, prices, and FAQs.
Save it.
3. Install + test it
Open Terminal, go into the folder, and run:
npm install
npm run checkYou should see โ Your kit looks good!
4. Try it in your browser first (the fun part) ๐ฎ
Before touching any AI app, run:
npm run playThen open http://localhost:4321. You'll get a simple page where you can:
Edit your business info in a form (no JSON, no code) and Save
Try the tools live โ ask "What are your hours?", get a price quote, look up an FAQ โ and see the exact answers your AI will give
This is the same logic the AI uses, so if it works here, it works there.
Press Ctrl+C in Terminal to stop the playground.
5. Connect it to your AI
In Claude Desktop: Settings โ Developer โ Edit Config, and add this (change the path to where you unzipped the folder):
{
"mcpServers": {
"my-business": {
"command": "node",
"args": ["/full/path/to/mcp-starter-kit/server.js"]
}
}
}Restart Claude Desktop. You'll see your business tools appear. Now ask it a question about your business โ and watch it use the real answer. ๐
The 5 questions to ask before you connect AI to anything
Before you wire AI into your real tools (email, CRM, calendar, payments), ask:
What can it actually do? โ Read-only, or can it change/delete things? (This kit is read-only on purpose.)
What data does it touch? โ And is any of it sensitive?
Where does that data go? โ Stays on your machine, or sent to a company?
Who can use it? โ Just you, or your whole team / your customers?
What happens if it's wrong? โ What's the worst-case, and can you undo it?
If you can't answer these for a tool someone's trying to sell you โ slow down.
Make it yours
Everything lives in business.json โ no coding needed to update your info.
Want it to do more (real bookings, live inventory, connect to your CRM or
email)? That's exactly the kind of thing we build.
๐ Built by Rabbithole โ rabbithole.consulting
We help small and medium businesses put AI to work โ safely, and in plain English. This is Day 1 of our 30-day series of free, working AI kits.
Want this set up for your business, with your real tools connected? ๐ rabbithole.consulting
Free to use under the MIT License. Built to be opened, edited, and run by real business owners.
Available Tools
4 toolscheck_availabilityCheck availabilityA
Returns the currently open appointment or booking slots. Use this when a customer wants to book or asks what times are available.
Inputs: no named parameters.
get_business_infoGet business infoA
Returns the business name, contact details, address, and opening hours. Use this to answer questions about the business itself.
Inputs: no named parameters.
lookup_faqLook up an FAQA
Searches the business's frequently asked questions for the best match. Use this for common customer questions (wifi, parking, catering, etc.).
Inputs: question (required).
price_quotePrice a quoteA
Given a service name and quantity, returns the price and a calculated total. Use this when a customer asks how much something costs.
Inputs: service (required), quantity.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogโฆ
TDQS
Scored across 4 tools
Each tool maps to a distinct resource and intent: business metadata, pricing, FAQ search, and slot availability. There is no realistic overlap that would cause misselection, and descriptions reinforce the boundaries.
All names use snake_case with a leading verb (get_, price_, lookup_, check_), which is consistent and readable. The only minor deviation is get_business_info's three-part name and price_quote's imperative-noun form, but the pattern remains predictable overall.
Four tools is on the low side but appropriate for a lightweight starter kit aimed at basic customer inquiries. Each tool earns its place without redundancy, though the surface is minimal.
The set covers info, price, FAQ, and availability lookups, but there is no tool to actually create or confirm a booking, which is an obvious dead end given check_availability. Adding a booking/contact tool would round out the customer-service lifecycle.
Maintenance
Related MCP Connectors
Hosted MCP server connecting AI assistants to 9,000+ apps and 40,000+ actions via Zapier.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
The HubSpot MCP Server acts as a bridge that enables AI assistants and Large Language Models to securely interact with HubSpot CRM data through natural conversation, without requiring users to understand complex API structures. It provides read-only access to standard CRM objects (contacts, companies, deals, tickets, products, invoices, and more) and their associations, secured via OAuth 2.0, allowing AI agents to perform tasks like summarizing deals, fetching company updates, and looking up record changes.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
Related MCP Servers
- AlicenseCqualityDmaintenanceA starter kit for building Model Context Protocol servers that enables AI tools to access external data and functionalities like checking holidays, disk space, timezones, RSS feeds, code diffs, and web performance metrics.12ISC
- AlicenseNot gradedqualityDmaintenanceA starter template for building MCP servers that enable AI assistants to interact with custom tools and data.8 npmMIT
- FlicenseNot gradedqualityDmaintenanceDemo MCP server that exposes order and customer data as read-only tools for AI assistants, simulating a business API or internal data source.-
- AlicenseAqualityDmaintenanceA read-only MCP server that lets AI assistants answer Shopify store operations questions via tools like get_shop, list_products, get_product, and list_orders.4MIT