ZenMaid MCP Server and API by Cotlet

dev.cotlet由 cotlet.dev 发布官方发布者v1.0.2更新于 Nov 11, 2026

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

发布方自己的服务:Cotlet

已验证Streamable HTTP可网页运行效率与工作流商业与电商

概览

AI 生成的概览

托管在 Cotlet.dev 的 MCP 服务器,让 AI 助手在 ZenMaid 清洁业务账户中创建和改约预约。

可以做什么
  • 创建和改约预约,包括为新老客户安排周期性服务
  • 按服务时长查询空档并按天列出
  • 新增和更新客户资料、地址与周期性排期
  • 找出未来一段时间没有预约的周期客户及其上次清洁日期
  • 把某位员工的预约转给另一位并列出受影响的客户
适用场景
适合使用 ZenMaid 经营清洁业务、希望用自然语言直接排班、改约或核查客户与预约,而不必在应用里逐项点击的用户。
运行要求
可通过 streamable HTTP 连接 cotlet.dev 远程端点,或用 zenmaid-mcp(PyPI,需 Python 3.10+)或 Docker 在本地以 stdio 运行。需要 Cotlet API 密钥,通过 Authorization Bearer 请求头或本地服务器的 COTLET_API_KEY 环境变量提供,并需在 Cotlet.dev 中登录并连接 ZenMaid 账户。
安装前请注意
Authorization 请求头中的 Cotlet API 密钥可访问你的 ZenMaid 账户,务必保密。工具会创建和修改预约与客户记录,批量转移或修改前应先确认。请求与账户数据会经过第三方 Cotlet.dev 服务,并由其代为操作你的 ZenMaid 账户。

安装

在 SourceWeft 中

  1. 打开 控制台中的 ZenMaid MCP Server and API by Cotlet,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/dev.cotlet%2Fzenmaid/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "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

来源:README.md,提交 2f38dc8

工具

0
SourceWeft 尚未读取此服务器的工具。

版本历史

1
  1. v1.0.2最新Nov 11, 2026

评分

已满足适用检查项的 75%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

    请在仓库或注册中心条目中声明许可证。

其他 Cotlet 集成