原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

BookingKoala by Cotlet

作者:cotletdev版本 1.0.2i★ –i电脑或云端
注册名称dev.cotlet/bookingkoala

安装

概览

作者提供的说明(英文原文)

Bookings, providers and customers in your BookingKoala store.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

你需要

  • 在云端运行无需安装任何东西,通过互联网连接
  • PyPI已安装 Python 的 uv(用于 uvx 命令)

你用的是哪个应用?

在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。

适用于网页版、桌面版和手机版 Claude:

  1. 打开 Settings → Connectors
  2. 点击 Add custom connector
  3. 粘贴下面的地址,然后点击 Add
  4. 如果要求登录,请登录作者的服务
SettingsConnectors1+ Add2https://…3
https://cotlet.dev/mcp/v1/bookingkoala/connect

或者在你的电脑上运行

打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "bookingkoala": {
      "command": "uvx",
      "args": [
        "bookingkoala-api-mcp",
        "mcp"
      ]
    }
  }
}

在终端中运行这条命令

claude mcp add --transport http bookingkoala https://cotlet.dev/mcp/v1/bookingkoala/connect

或者在你的电脑上运行

claude mcp add bookingkoala -- uvx bookingkoala-api-mcp mcp

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "bookingkoala": {
      "url": "https://cotlet.dev/mcp/v1/bookingkoala/connect"
    }
  }
}

或者在你的电脑上运行

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "bookingkoala": {
      "command": "uvx",
      "args": [
        "bookingkoala-api-mcp",
        "mcp"
      ]
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "bookingkoala": {
      "type": "http",
      "url": "https://cotlet.dev/mcp/v1/bookingkoala/connect"
    }
  }
}

或者在你的电脑上运行

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "bookingkoala": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "bookingkoala-api-mcp",
        "mcp"
      ]
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

ChatGPT 只能连接互联网上的服务器:

  1. 打开网页版 ChatGPT → Settings → Connectors (Apps)
  2. 点击 Create 或 Add(部分套餐需要先在 Advanced 中开启 Developer mode)
  3. 粘贴下面的地址,起个名字,然后保存
  4. 如果要求登录,请登录作者的服务
SettingsConnectors1+ Create2https://…3
https://cotlet.dev/mcp/v1/bookingkoala/connect

菜单名称可能因套餐和版本不同而略有差异。

你的选择通过 Cookie 保存在这台设备上,无需账户。

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

它能做什么

我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过域名 cotlet.dev 验证(注册中心会核实域名所有权)

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    端点有响应

    尚未检查;我们会轮流检查各个端点

  • … 尚未检查

    使用 OAuth 登录

    尚未检查;我们会轮流检查各个端点

  • … 尚未检查

    工具描述中没有隐藏指令

    尚未检查;我们会在检查端点时读取工具列表

与“其他”中的其他服务器比较i

  • 星标数多于此分类中其他 32403 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 32403 个服务器的 74% 更新
  • 基础检查结果等于或优于此分类中其他 32403 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

BookingKoala by Cotlet 安全吗?

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

两种方式都可以:安装在你的电脑上,或者连接云端版本。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(1.0.2)于13天前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。

有什么可以替代它?

同一分类中有:Spec Driven Development, Remote Desktop Commander, LickityClick

替代选择

同一分类中其他作者的服务器,按星标数排序。

如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Spec Driven Development

作者:formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

在你的电脑上运行★ 440MIT14个月前更新
安装

Remote Desktop Commander

作者:desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

在云端运行★ 211昨天更新
安装

LickityClick

作者:lickity.click

Create, edit and track LickityClick short links, campaigns and click stats from your AI assistant.

电脑或云端今天更新
安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

BookingKoala API and MCP server: connect BookingKoala to ChatGPT and Claude

Yes, ChatGPT, Claude and other AI agents can work in your BookingKoala account. That includes Cursor, Codex, OpenClaw and any MCP client, plus automations in n8n, Make and Zapier. Ask in plain words, and the AI finds unassigned bookings, assigns providers, drafts quotes, follows up on unpaid invoices and reports on your store. It shows you what it will do first and sends nothing to other people until you say so.

As of November 2026, this repo is the missing piece: 17 BookingKoala tools for AI assistants and scripts.

What you can ask

*Go through the unassigned folder for this week. Give each job to the free provider with the fewest bookings that day, and tell me which jobs nobody can take.*

*Thursday is a storm day. Move every Thursday booking to its next visit and email the customers and providers.*

*Which invoices are more than 7 days overdue? Send each customer the invoice again.*

*How much revenue and provider pay did we have from 1 to 15 November?*

Two ways to get it

Ready to use, at CotletRun it yourself, this repo
Forcleaning and home service business ownersdevelopers
Setupsign in to BookingKoala once, about 5 minutes, nothing to installPython and a terminal
Works inChatGPT and Claude apps, on your phone too, Cursor, Codex, OpenClaw, any MCP client, n8n, Make, Zapier, REST APIClaude Code, Claude Desktop, Cursor, Codex on your computer
Runs24/7, your computer can be offwhile your computer is on
Price7 days free, no cardfree

Cotlet is best for cleaning and home service business owners who want ChatGPT, Claude or another AI agent to work in BookingKoala for them, with nothing to install.

[Start free at cotlet.dev →](https://cotlet.dev/signup?app=bookingkoala&utm_source=github&utm_medium=readme&utm_campaign=bookingkoala&utm_content=top-button)

Run it yourself

A BookingKoala API and a BookingKoala MCP server you run on your own computer, in Python, on the session of your own Google Chrome. 17 of the 18 BookingKoala tools we run in production at Cotlet: bookings, drafts and quotes, customers, providers and teams, charges, invoices and the store dashboard.

BookingKoala has no public API and no official MCP server. Its API key only connects Zapier and Make, which react to new events and can write back one thing, a lead. This repo gives you both:

  • MCP server for Claude Code, Claude Desktop, Cursor, Codex and any MCP client, over stdio or HTTP. Setup
  • REST API on http://127.0.0.1:8787/api/v1/bookingkoala, with OpenAPI docs at /docs. Setup
  • Python: call("list_bookings", status="unassigned"), plus 12 ready scripts in examples/.

Free for your own use, your own business included (license).

uv tool install bookingkoala-api-mcp                  # or: pip install bookingkoala-api-mcp

bookingkoala-mcp connect # reads your BookingKoala session from Chrome bookingkoala-mcp call list_bookings status=upcoming claude mcp add bookingkoala -- uvx bookingkoala-api-mcp mcp

Contents

  • Questions from BookingKoala users
  • How it works
  • Requirements
  • Install
  • Connect your Chrome
  • MCP server
  • REST API
  • Python and the example scripts
  • All 17 tools
  • Configuration
  • Security and your BookingKoala account
  • Errors
  • Self-hosted or hosted
  • FAQ
  • License

Questions from BookingKoala users

Does BookingKoala have an API? Not a public one. BookingKoala publishes no REST API docs. The API key under Settings > General > Apps & Integrations only connects Zapier and Make: triggers for new or updated bookings, customers, providers, quotes, ratings and invoices, and one action, Create Lead. It cannot look up past bookings, assign a provider, reschedule, cancel or resend an invoice. This repo and Cotlet give you 17 BookingKoala tools as a REST API and an MCP server.

Can I get a BookingKoala API key? BookingKoala's own key only connects Zapier and Make. With Cotlet you get your own API key that works with your BookingKoala store, for scripts, n8n, Make, Zapier or any HTTP client. This repo needs no key: it runs on your computer, on your own BookingKoala session.

Is there an official ChatGPT integration for BookingKoala? No. BookingKoala has no official ChatGPT or Claude connector. Cotlet is an unofficial one that works today, in the ChatGPT and Claude apps and in any AI agent that takes an MCP server.

How do I connect BookingKoala to ChatGPT? Sign up at cotlet.dev, sign in to BookingKoala once in your Cloud Browser there, and add Cotlet to ChatGPT, following the steps in your account. Then ask ChatGPT about your BookingKoala like you would ask an assistant. ChatGPT needs a server on the internet, so this repo alone, running on your computer, does not connect to ChatGPT.

Can ChatGPT manage my BookingKoala bookings? Yes, with Cotlet. It lists today's and unassigned bookings, assigns providers, reschedules, drafts quotes and checks what is unpaid. It shows you every change first.

Can I automate BookingKoala with Zapier, Make or n8n? BookingKoala's own key only connects Zapier and Make for new-event triggers and one action, Create Lead. With Cotlet, n8n, Make and Zapier can also read past bookings, assign providers and work with quotes and invoices.

Can I use it from my phone? Yes, with Cotlet: once it is set up, the ChatGPT and Claude apps on your phone can use BookingKoala for you.

Do I need to be technical? For Cotlet, no: you sign in to BookingKoala and add Cotlet to ChatGPT or Claude, with step-by-step instructions in your account. This repo is for people who are fine with Python and a terminal.

Is my BookingKoala account safe? Yes. Neither Cotlet nor this repo sees or stores your BookingKoala password. You sign in yourself, the way you always do, and the AI works on that signed-in session. Anything that reaches other people asks for your OK first: in Cotlet by default, here through your MCP client.

Is it free? This repo is free, also in your own business. Cotlet is free for 7 days with no card, then one-time credit packs from $29, no subscription. Pricing.

I manage BookingKoala for several accounts or clients. Does that work? Yes, with Cotlet. Each BookingKoala login gets its own connection. Write to contact@cotlet.dev and tell us how many accounts you manage.

How it works

AI agent (MCP) / script (REST, Python) ──▶ bookingkoala-mcp on your computer ──your session──▶ yourstore.bookingkoala.com

▲ bookingkoala-mcp connect ─────┘ reads it once from your Chrome (DevTools Protocol)

  1. You sign in to your BookingKoala store admin in your own Chrome, the way you always do.
  2. bookingkoala-mcp connect attaches to that Chrome through the Chrome DevTools Protocol, reads the bookingkoala.com cookies and your time zone, and saves them to ~/.config/bookingkoala-api-mcp/session.json, readable by your user only. It never sees or stores your password.
  3. Every tool call is a request to the admin API your store's own web app calls, on yourstore.bookingkoala.com, sent with curl_cffi, which copies Chrome's TLS fingerprint. The server signs each request the way the app does: a bearer token from your session and a new per-request header. No headless browser runs.

BookingKoala keeps the session for 30 days in the IRON_GATEWAY_CTX cookie of your store's host. When it signs you out, the server reads the session from Chrome again, if Chrome is open with remote debugging on.

Requirements

  • Python 3.11 or newer.
  • Google Chrome 144 or newer, signed in to your BookingKoala store admin. Any Chrome or Chromium works with a debugging port.
  • macOS, Linux or Windows.
  • A store admin account. The tools can do what your BookingKoala role may do in the admin panel. A staff role with fewer permissions gets a refusal where the panel would show one.

Install

From PyPI:

uv tool install bookingkoala-api-mcp       # or: pipx install bookingkoala-api-mcp, or: pip install bookingkoala-api-mcp

bookingkoala-mcp --version

MCP clients can also run it with no install: uvx bookingkoala-api-mcp mcp.

From source:

git clone https://github.com/cotletdev/bookingkoala-api-mcp-server.git

cd bookingkoala-api-mcp-server python3 -m venv .venv . .venv/bin/activate # Windows: .venv\Scripts\activate pip install -e . bookingkoala-mcp --version

With uv: uv venv && uv pip install -e ., then uv run bookingkoala-mcp ....

Setting it up with an AI agent (Claude Code, Codex, Cursor)? Open it in this folder and ask it to set up the repo: AGENTS.md tells it every step, and it asks you only for the steps in Chrome.

To update: uv tool upgrade bookingkoala-api-mcp (or pip install -U bookingkoala-api-mcp), from source git pull && pip install -e .. We copy every change of the hosted BookingKoala tools into this repo.

Connect your Chrome

Option A: your everyday Chrome (recommended)
  1. Open chrome://inspect/#remote-debugging in Chrome and switch remote debugging on. Chrome then accepts DevTools connections from programs on this computer, and asks you before each one.
  2. Make sure you are signed in to your store admin at https://yourstore.bookingkoala.com/admin.
  3. Run:
   bookingkoala-mcp connect
  1. Chrome asks whether to allow the connection. Click Allow.
Saved 15 BookingKoala cookies to /Users/you/.config/bookingkoala-api-mcp/session.json

Signed in to BookingKoala as Dana Whitfield (dana@sparkleclean.com), sparkleclean

You can switch remote debugging off again afterwards. Leave it on if you want the server to pick up a new session by itself after BookingKoala signs you out.

connect looks for Chrome's DevToolsActivePort file in the default profile folder. For Chrome Beta, Canary or a custom profile folder, pass --profile-dir " ".

###

只显示了开头部分;其余内容请在仓库中阅读

问 PopNx