FrontDesko MCP Server
FrontDesko MCP 服务器
一个公开的 Model Context Protocol 服务器,用于 FrontDesko —— 面向独立酒店、B&B、民宿、青年旅舍和小型连锁酒店的简单、免费、现代化的酒店 PMS。
端点地址: https://mcp.frontdesko.app/mcp(Streamable HTTP,无需认证,只读)
将其添加到你的 AI 助手并询问真实问题——"一家 20 间客房的酒店每年要付给 OTA 多少钱?""FrontDesko 对比 Cloudbeds?""肯尼亚一家 12 间客房的民宿该选哪个方案?"——即可获得基于 FrontDesko 公开页面的答案,并附带来源 URL。
快速开始
Claude Code
claude mcp add --transport http frontdesko https://mcp.frontdesko.app/mcpClaude Desktop / 其他 MCP 客户端(mcpServers 配置):
{
"mcpServers": {
"frontdesko": {
"type": "http",
"url": "https://mcp.frontdesko.app/mcp"
}
}
}Cursor —— 设置 → MCP → 添加服务器 → URL https://mcp.frontdesko.app/mcp。
Related MCP server: Crawl4AI RAG MCP Server
工具
工具 | 功能简介 |
| FrontDesko 的方案:PMS、直订引擎、宾客应用和 POS 永久免费(不限房间数);渠道管理器 + Ask FrontDesko AI 助手仅限 Growth 版(每月 $42,10–30 间客房)和 Professional 版(每月 $54,30–50 间客房) |
| 与 Cloudbeds、eZee Absolute、Hotelogix、Little Hotelier 或 Mews 的逐项功能对比——数据来自 FrontDesko 已发布的对比页面 |
| 一家酒店每年付给 OTA 的费用,以及将 30% 的预订转化为免佣金直订后可挽回的金额——公式与网站计算器相同 |
| 按物业类型(16 种)、房间数和国家(24 个国家指南)推荐方案和指南 |
| 对 frontdesko.app/llms-full.txt 进行全文搜索,附带摘录和来源 URL |
| FrontDesko 公开演示物业的实时房态——数据来自每家 FrontDesko 酒店免费获得的同一预订引擎 |
所有工具均为只读。不会写入任何数据、不会创建任何预订,服务器也不会存储关于你的任何信息。
关于数据
答案来自 FrontDesko 自己发布的页面,每个响应都包含其来源 URL。竞品对比数据反映了各对比页面上注明的公开信息。演示房态工具查询的是专用演示物业(每个调用者限流 10 次/分钟)。
开发
npm install
npm test # 23 tests: unit + e2e over the real Streamable HTTP transport
npm run dev # wrangler dev → http://localhost:8787/mcp
npm run smoke # SDK client against a running server (local or prod)
npm run check-urls # verifies every data URL is live and pricing hasn't drifted基于 Cloudflare Worker 构建,使用 agents 的createMcpHandler 和 MCP TypeScript SDK。
FrontDesko
FrontDesko 是一款酒店管理软件,采用一种不寻常的模式:核心功能——PMS、免佣金直订引擎、宾客应用、POS——永久免费且不限房间数。付费方案仅针对两项功能:OTA 渠道管理器和 Ask FrontDesko AI 助手。
许可证
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceScrapes and indexes documentation websites to provide AI assistants with searchable access to documentation content, API references, and code examples through configurable URL crawling.
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to crawl websites, extract and store web content with semantic search capabilities using vector embeddings, and retrieve information through natural language queries with tag-based filtering and intelligent content cleaning.
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to query and retrieve topic-specific knowledge from recursively crawled and indexed web pages.26311MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to query PDF documents by ingesting them into a vector database and generating answers grounded in the actual documents.111MIT
Related MCP Connectors
Shared knowledge base for AI agents. Semantic search across agents, no setup required — just a URL.
Connect your team's living knowledge base — docs, data, issues, CRM — to Claude and ChatGPT.
Vacation rental discovery, direct booking, and property protection for AI agents.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/anmols/frontdesko-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server