ZenMaid MCP Server and API by Cotlet

dev.cotlet由 cotlet.dev 發布官方發布者v1.0.2更新於 Nov 11, 2026

ZenMaid cleaning business scheduling MCP server: create appointment, reschedule appointment.

發布方自己的服務:Cotlet

已驗證Streamable HTTP可網頁執行效率與工作流商業與電商

概覽

AI 產生的概覽

託管於 Cotlet.dev 的 MCP 伺服器,讓 AI 助理在 ZenMaid 清潔業務帳戶中建立與改期預約。

可以做什麼
  • 建立與改期預約,包含為新舊客戶安排週期性服務
  • 依服務時長查詢空檔並按天列出
  • 新增與更新客戶資料、地址與週期性排程
  • 找出未來一段時間沒有預約的週期客戶及其上次清潔日期
  • 把某位員工的預約轉給另一位並列出受影響的客戶
適用情境
適合以 ZenMaid 經營清潔業務、希望用自然語言直接排班、改期或查核客戶與預約,而不必在應用程式裡逐項點選的使用者。
執行需求
可透過 streamable HTTP 連線 cotlet.dev 遠端端點,或以 zenmaid-mcp(PyPI,需 Python 3.10+)或 Docker 在本機以 stdio 執行。需要 Cotlet API 金鑰,透過 Authorization Bearer 標頭或本機伺服器的 COTLET_API_KEY 環境變數提供,並需在 Cotlet.dev 中登入並連結 ZenMaid 帳戶。
安裝前請注意
Authorization 標頭中的 Cotlet API 金鑰可存取你的 ZenMaid 帳戶,務必保密。工具會建立與修改預約及客戶資料,批次轉移或修改前應先確認。請求與帳戶資料會經過第三方 Cotlet.dev 服務,並由其代為操作你的 ZenMaid 帳戶。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 ZenMaid MCP Server and API by Cotlet,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/dev.cotlet%2Fzenmaid/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "zenmaid-and-api-by-cotlet": {
      "type": "http",
      "url": "https://cotlet.dev/mcp/v1/zenmaid/connect"
    }
  }
}

README

How to connect ZenMaid to Claude Code, ChatGPT and any AI agent

Yes, Claude, ChatGPT and other AI agents can work in your ZenMaid account. ZenMaid has no official app in the ChatGPT or Claude directories, and its documentation points integrations to Zapier. Cotlet.dev connects your own signed-in ZenMaid account to any AI agent, so you can ask in plain words and the AI schedules jobs, finds openings and updates customers for you.

What you can ask

Schedule a 3-hour deep clean for Maria Lopez at 42 Oak Street on Thursday at 9 am with Team B.

Where are the open slots next week for a 2-hour standard clean? List them by day.

Add a new customer, David Chen at 18 Pine Ave, with a biweekly clean every other Monday at 1 pm.

Which recurring customers have no job booked in the next 30 days? Show their last clean date.

Move all of Kelly's Friday jobs to Rosa and list the customers affected.

Connect in 2 minutes

Get your API key at https://cotlet.dev/app and export it as COTLET_API_KEY.

Claude Code

bash
claude mcp add --transport http cotlet https://cotlet.dev/mcp/v1 --header "Authorization: Bearer $COTLET_API_KEY"

ChatGPT

Settings → Apps → add connector URL https://cotlet.dev/mcp/v1, then sign in with Cotlet.dev. No API key needed.

Cursor

Copy .cursor/mcp.json from this repo into your project:

json
{  "mcpServers": {    "cotlet": {      "url": "https://cotlet.dev/mcp/v1",      "headers": {        "Authorization": "Bearer ${COTLET_API_KEY}"      }    }  }}

Run it locally (stdio)

This repo is a real MCP server. It speaks MCP over stdio, lists its ZenMaid tools without any key, and forwards every tool call to the hosted Cotlet.dev server. The hosted URL above stays the recommended way. Use this when your client only starts local servers.

json
{"mcpServers":{"zenmaid":{"command":"uvx","args":["zenmaid-mcp"],"env":{"COTLET_API_KEY":"your-key"}}}}

Or with Docker:

bash
docker build -t zenmaid-mcp .docker run -i --rm -e COTLET_API_KEY zenmaid-mcp

Tools: zenmaid_guide, zenmaid_status, zenmaid_open, zenmaid_read, zenmaid_click, zenmaid_type, zenmaid_close. Without COTLET_API_KEY a tool call answers: "Set COTLET_API_KEY. Get a key at https://cotlet.dev/app".

Command line

Python 3.10+, nothing else to install. From PyPI:

bash
pip install zenmaid-mcp        # or run it once: uvx zenmaid-mcp connectzenmaid-mcp connect

Or straight from this repo:

bash
export COTLET_API_KEY="your-key"python3 zenmaid_agent.py connect   # ready config for Claude Code, Cursor, ChatGPTpython3 zenmaid_agent.py status    # is ZenMaid ready in your Cotlet.dev accountpython3 zenmaid_agent.py guide     # ZenMaid screens and sign-in linkpython3 zenmaid_agent.py read      # open ZenMaid, read the page, close the browserpython3 zenmaid_agent.py tools     # list Cotlet.dev toolspython3 zenmaid_agent.py serve     # start the stdio MCP server (same as no argument)

Questions from ZenMaid users

Does ZenMaid have an API?

ZenMaid's documentation directs integrations through Zapier. Cotlet.dev works in your ZenMaid account directly, so your AI agent can schedule jobs and manage customers without setting up Zaps.

How do I connect ZenMaid to ChatGPT?

Add Cotlet.dev as an app in ChatGPT (Settings → Apps, connector URL https://cotlet.dev/mcp/v1), sign in to ZenMaid once in your Cotlet.dev Cloud Browser, and ask ChatGPT in plain words. No code and no ZenMaid API key.

Is there a way to use Claude with ZenMaid?

Yes. In Claude Code run the one-line claude mcp add command above; in the Claude app add https://cotlet.dev/mcp/v1 as a custom connector. Claude then works in your own ZenMaid account.

Is there a ZenMaid MCP server?

ZenMaid has no official MCP server. Zapier offers a third-party ZenMaid MCP connection. Cotlet.dev is a hosted MCP server that works in ZenMaid for you, 24/7, with Claude, ChatGPT, Cursor, Codex, n8n, Make and Zapier.

Find it on

Also works with


More: https://cotlet.dev/integrations/zenmaid-api-mcp-server?utm_source=github&utm_medium=readme&utm_campaign=zenmaid

Start free: https://cotlet.dev/signup?app=zenmaid&utm_source=github&utm_medium=readme&utm_campaign=zenmaid

來源:README.md,提交 2f38dc8

工具

0
SourceWeft 尚未讀取此伺服器的工具。

版本歷史

1
  1. v1.0.2最新Nov 11, 2026

評分

已滿足適用檢查項的 75%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

    請在儲存庫或註冊中心條目中宣告授權條款。

其他 Cotlet 整合