bearing-local-business
Enables AI agents to query a local bakery's hours, menu, custom-order availability, and submit demo inquiries through a clean MCP interface.
README
bearing-local-business
bearing-local-business is a Bearing reference stdio MCP server for a fictional bakery, Cypress & Crumb. It makes a local business agent-queryable so a customer's AI agent can check hours, inspect the menu, ask about custom-order timing, and initiate a demo inquiry.
All data is fictional demo data. The server makes no network calls, persists nothing, and is intended as a reference for the agentic economy: a local business exposing a clean, typed MCP surface for discovery and transaction initiation.
Tools
get_business_profile
- Input: none
- Output: bakery name, tagline, weekly hours, address, phone, pickup details, delivery details, and custom-order lead time
get_menu
- Input:
{ category?: string } - Output: the full menu grouped by category, or the filtered category if provided
check_custom_order_availability
- Input:
{ date: string, orderType?: string } - Output: whether the requested date is far enough out for a custom order, the integer days out, and the earliest available date
submit_order_inquiry
- Input:
{ name: string, contact: string, details: string, date?: string } - Output: a demo inquiry reference plus the captured request details
Run
Development:
bun run dev
Build and run the compiled server:
bun run build
bun run start
The server reads src/data/demo-bakery.json at runtime with readFileSync and import.meta.url path resolution. The loader checks both the source-layout path used by bun run src/index.ts and the built-layout path used by node dist/index.js, so the JSON file does not need to be copied into dist/.
MCP Client Config
Example Claude Desktop or compatible stdio client config:
{
"mcpServers": {
"bearing-local-business": {
"command": "node",
"args": [
"/absolute/path/to/bearing-mcp/dist/index.js"
]
}
}
}
For local development, you can also point a client at Bun:
{
"mcpServers": {
"bearing-local-business": {
"command": "bun",
"args": [
"run",
"/absolute/path/to/bearing-mcp/src/index.ts"
]
}
}
}
Point It At A Real Business
To adapt this for a real business, replace the fictional demo-bakery.json source with a consented, authenticated system of record such as a POS, ordering backend, or inventory service. In a real deployment:
- keep the MCP tool contracts stable
- add authentication and authorization
- persist inquiries into the business's system
- fetch live hours, menu, and availability from an approved source
This demo intentionally does none of that. It persists nothing and only echoes a simulated inquiry capture.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.