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.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。