monday-mcp

monday-mcp

A lightweight MCP server that provides a focused set of tools for interacting with monday.com's GraphQL API, enabling users to manage boards, items, users, and updates from AI assistants.

Category
访问服务器

README

monday-mcp

A lightweight, independent Model Context Protocol (MCP) server for interacting with the monday.com GraphQL API from MCP-compatible AI assistants and development tools. It exposes a focused set of explicit, validated tools and sends fixed GraphQL operations to monday.com; clients cannot inject arbitrary GraphQL.

What is monday-mcp?

monday-mcp is a lightweight Python MCP server that provides a focused set of tools for common monday.com workflows. It is built around:

  • A standard MCP interface over stdio.
  • Predefined GraphQL operations for users, teams, workspaces, boards, groups, columns, items, and updates.
  • Explicit confirmWrite: true confirmation for every data-changing tool.
  • Straightforward local configuration through the MONDAY_API_TOKEN environment variable.

It is an independent open-source project and is not affiliated with, endorsed by, sponsored by, or maintained by monday.com Ltd.

Features

  • Identify the authenticated user and search users and teams.
  • List workspaces and boards; inspect a board's groups and columns.
  • List board items with cursor pagination; retrieve an item and its updates.
  • Create items, rename them, update their column values, and move them between groups.
  • Post updates and replies.
  • Require confirmWrite: true for every data-changing tool.
  • Keep the API token in the MCP client's environment, not in command-line arguments.
  • Use standard stdio MCP transport.

Architecture

flowchart TD
  A["MCP client or AI assistant"] --> B["monday-mcp (stdio)"]
  B --> C["monday.com GraphQL API"]
  C --> D["monday.com workspace"]

Quick start

git clone https://github.com/<your-account>/monday-mcp.git
cd monday-mcp
uv sync

Create a monday.com personal API token with access to the boards and users you need. Then add this server to an MCP client configuration:

{
  "mcpServers": {
    "monday-mcp": {
      "command": "uv",
      "args": [
        "run",
        "--project",
        "/absolute/path/to/monday-mcp",
        "monday-mcp"
      ],
      "env": {
        "MONDAY_API_TOKEN": "replace_with_your_monday_api_token"
      }
    }
  }
}

Restart or reload the MCP client, then ask it to list your boards, inspect a board, create an item, update its status, or move it to another group. See installation for a complete setup and examples for prompts.

Configuration

MONDAY_API_TOKEN is required. Set it in your MCP client's env configuration; do not commit a real token or pass one on the command line. See configuration.

Documentation

Security

The server reads the token only from MONDAY_API_TOKEN at startup and sends it only as the authorization header for requests to https://api.monday.com/v2. Every tool that creates or modifies data requires confirmWrite: true; grant the token only the access it needs. See SECURITY.md.

Roadmap

Version 1.0.0 supports essential workspace, board, item, user/team, and update workflows. It intentionally does not expose arbitrary GraphQL, board administration, file upload, OAuth, webhooks, or account administration.

Contributing

Contributions are welcome. Read CONTRIBUTING.md before opening a pull request.

Disclaimer

This is an independent open-source project and is not affiliated with, endorsed by, sponsored by, or maintained by monday.com Ltd.

monday.com is a trademark of monday.com Ltd.

License

This project is licensed under the MIT License.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选