Book4Time MCP Server
Enables interaction with the Book4Time API through an Azure Function-hosted server. It allows users to query product information and manage bookings using MCP-compatible clients like Claude Desktop.
README
Book4Time MCP Server — Azure Function App
File structure
mcp_azure/
├── function_app.py # Azure Function entry point + HTTP trigger
├── mcp_server.py # FastMCP server + product tool
├── requirements.txt # Python dependencies
├── host.json # Azure Functions host config
├── local.settings.json.template # Copy → local.settings.json for local dev
└── README.md
How it works
- MCP client (e.g. Claude Desktop) sends a JSON-RPC
POSTto your Azure Function URL. function_app.pycatches the request via themcp/{*path}HTTP trigger.- The request is forwarded into FastMCP's Streamable HTTP ASGI app.
- FastMCP routes it to the
producttool inmcp_server.py. - The tool calls the Book4Time API with your credentials from App Settings.
- The JSON response travels back up the chain to the MCP client.
Local development
# 1. Install dependencies
pip install -r requirements.txt
# 2. Configure secrets
cp local.settings.json.template local.settings.json
# Edit local.settings.json — fill in BOOK4TIME_API_TOKEN and BOOK4TIME_ACCOUNT_TOKEN
# 3. Start the Functions runtime
func start
The MCP endpoint will be at:
http://localhost:7071/api/mcp
Deploy to Azure
# 1. Create resource group and Function App (one-time)
az group create --name rg-book4time-mcp --location uksouth
az functionapp create \
--resource-group rg-book4time-mcp \
--consumption-plan-location uksouth \
--runtime python \
--runtime-version 3.11 \
--functions-version 4 \
--name <YOUR_APP_NAME> \
--storage-account <YOUR_STORAGE_ACCOUNT>
# 2. Set the API tokens as App Settings (not in code)
az functionapp config appsettings set \
--name <YOUR_APP_NAME> \
--resource-group rg-book4time-mcp \
--settings \
BOOK4TIME_API_TOKEN="your_real_api_token" \
BOOK4TIME_ACCOUNT_TOKEN="your_real_account_token"
# 3. Deploy the code
func azure functionapp publish <YOUR_APP_NAME>
The live MCP endpoint will be:
https://<YOUR_APP_NAME>.azurewebsites.net/api/mcp
Connect from Claude Desktop
In claude_desktop_config.json:
{
"mcpServers": {
"book4time": {
"url": "https://<YOUR_APP_NAME>.azurewebsites.net/api/mcp?code=<FUNCTION_KEY>"
}
}
}
Get your function key from the Azure Portal → Function App → App keys.
Adding more tools
Add new @mcp.tool() functions to mcp_server.py — they are automatically
discovered and registered. No changes needed in function_app.py.
@mcp.tool()
async def bookings(location_id: str = "11506000") -> dict:
"""Fetch bookings from Book4Time."""
...
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。
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。
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。
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。
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。
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。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
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