Partner Booking MCP Server

Partner Booking MCP Server

Simulates a third-party appointment booking agent, enabling your AI platform to check availability and book appointments via MCP interoperability.

Category
访问服务器

README

Partner Booking MCP Server (demo external agent)

A tiny, self-contained external MCP server that simulates a third-party vendor's appointment-booking agent. Point your platform's agent at its public URL to demonstrate real-time agent-to-agent interoperability — your agent orchestrating and exchanging tasks/context with an AI capability that is not hosted on your platform.

Transport: Streamable HTTP (stateless), so it deploys to any Node host and is reachable as a normal HTTPS endpoint.

Tools exposed

Tool What it does
check_availability Open slots for a service + date
book_appointment Books a slot, returns a confirmation id
cancel_appointment Cancels by confirmation id, frees the slot
list_appointments Lists bookings (optional customer filter)

Services seeded: haircut, dental-checkup, car-service, consultation. Dates seeded: 2026-07-27, 2026-07-28, 2026-07-29. (In-memory — resets on restart.)

Run locally

npm install
npm start          # -> http://localhost:3000/mcp

Quick smoke test:

curl -X POST http://localhost:3000/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'

Deploy to a public URL

Render (easiest — render.yaml included):

  1. Push this folder to a GitHub repo.
  2. Render → New → Blueprint → pick the repo. It reads render.yaml.
  3. You get a URL like https://partner-booking-mcp.onrender.com. Your MCP endpoint is https://.../mcp.

Railway / Fly / Cloud Run: same idea — Node app, start command node server.js, expose $PORT. A Dockerfile is included if the host prefers containers.

Free Render instances sleep when idle. Hit the URL once ~30s before the demo to wake it.

Connect it to your platform (the demo moment)

Register it as a remote MCP server in whatever your platform uses:

  • Endpoint / URL: https://<your-host>/mcp
  • Transport: Streamable HTTP
  • Auth: none (demo). Add a bearer-token check in server.js if your platform requires one.

To try it in a generic MCP client, the connection config looks like:

{
  "mcpServers": {
    "partner-booking": {
      "type": "http",
      "url": "https://<your-host>/mcp"
    }
  }
}

Suggested demo script

  1. User asks your platform's agent: "Book me a haircut next Monday morning."
  2. Your agent calls check_availability on this external server → shows the slots.
  3. Your agent calls book_appointment → returns confirmation BK-XXXXXXXX.
  4. Emphasise: the booking logic + data live in a separate, third-party service — your platform discovered its tools and orchestrated the task live over MCP.
  5. Optional: cancel_appointment to show a two-way, stateful exchange.

Notes for a production-shaped story

  • Add auth (bearer/OAuth) at the /mcp route.
  • Swap the in-memory store for a real DB/booking API.
  • Same pattern maps to any partner capability — this is intentionally minimal so the interoperability is the star, not the business logic.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选