🚀 monday.com MCP

Enable AI agents to operate reliably within real workflows. This MCP is monday.com's open framework for connecting agents into your work OS - giving them secure access to structured data, tools to take action, and the context needed to make smart decisions.

🌟 Overview

This repository, maintained by the monday.com AI team, provides a comprehensive set of tools for AI agent developers who want to integrate with monday.com. Whether you're building AI assistants, automations, or custom integrations, our tools make it easy to connect to the monday.com platform.

👉 New to monday MCP? Start here: monday.com/w/mcp

https://github.com/user-attachments/assets/ed8d24e1-256b-4f6b-9d84-38e54a8703fd

🔑 What is monday.com?

monday.com is a work operating system that powers teams to run processes, projects, and everyday work. Teams use monday.com to plan, track, and manage their work in one centralized platform. It provides a visual, intuitive interface where teams can:

• Create and manage projects with customizable boards
• Track tasks through different stages with status columns
• Collaborate with team members through updates and mentions
• Automate workflows and integrate with other tools
• Visualize data with dashboards and reports

📦 What's Inside

💻 monday API MCP Server

The @mondaydotcomorg/monday-api-mcp package provides a plug-and-play server implementation for the Model Context Protocol (MCP). It allows AI agents to interact with the monday.com API without needing to build complex integrations.

🤖 Agent Toolkit

The @mondaydotcomorg/agent-toolkit package provides a powerful set of tools and utilities for building AI agents that interact with the monday.com API, supporting both OpenAI and Model Context Protocol (MCP) implementations.

🧰 Available Tools

Our MCP server provides a rich set of tools that give AI assistants the ability to interact with monday.com:

🎨 monday.com Apps Framework Tools

Looking to build custom monday.com apps with AI assistance? The Apps Framework Tools provide AI agents with complete access to monday.com's app development platform, enabling you to create, manage, and deploy custom apps directly through AI assistants.

📖 View Full Apps Framework Tools Documentation

🔮 Dynamic API Tools (Beta)

Our Dynamic API Tools feature represents a significant advancement in how AI agents can interact with monday.com. While our standard tools cover common operations, Dynamic API Tools unlock the full potential of the monday.com GraphQL API.

What are Dynamic API Tools?

Dynamic API Tools provide AI agents with complete, adaptable access to monday.com's entire API surface. This means your AI assistant can:

1. Access any API endpoint - Not just the predefined operations we've built
2. Generate custom GraphQL queries - Create exactly the query needed for any situation
3. Dynamically explore monday.com's schema - Understand all available data types and their relationships

Key Dynamic API Tools

Unlocked Possibilities

With Dynamic API Tools, your AI assistants can:

• Create complex reports spanning multiple boards, items, and data points
• Perform batch operations across many items simultaneously
• Integrate deeply with monday.com's advanced features like docs, workspaces, and activity logs
• Discover new capabilities as monday.com adds features to their API

How to Enable

Dynamic API Tools are in beta and disabled by default. Enable them with:

MONDAY_TOKEN=your_monday_api_token npx @mondaydotcomorg/monday-api-mcp@latest --enable-dynamic-api-tools true

You can also use the 'only' mode to exclusively enable Dynamic API Tools:

MONDAY_TOKEN=your_monday_api_token npx @mondaydotcomorg/monday-api-mcp@latest --enable-dynamic-api-tools only

When 'only' mode is enabled, the server will provide just the Dynamic API Tools, filtering out all other standard tools. This is useful for advanced users who want to work directly with the GraphQL API.

⚠️ Note: Dynamic API Tools require full API access and are not compatible with read-only mode.

🔐 Authentication & Security

The server requires a monday.com API token to authenticate with the monday.com API. You can provide this token in two ways:

1. Environment variable: MONDAY_TOKEN=your_monday_api_token
2. Command line argument: -t your_monday_api_token

Security Best Practices

• Never share your API token in public repositories or discussions
• Consider using read-only mode (--read-only) when you only need to retrieve data
• Regularly rotate your API tokens for enhanced security

📚 Example Use Cases

Here are some examples of what you can build with our tools:

1. AI Assistant for Project Management

• Create and manage tasks in monday.com boards
• Get updates on project status
• Move items between groups as they progress

2. Data Analysis & Reporting

• Extract data from monday.com boards
• Generate reports and insights
• Create new boards for reporting

🌐 Community & Support

• GitHub Issues: For bug reports and feature requests
• Discussions: For questions and community discussions
• monday.com Developer Documentation: Learn more about the monday.com API

📚 Documentation

• monday API MCP Documentation
• Agent Toolkit Documentation
• monday.com API Reference

🛠️ How to develop in the repo

To develop for the repo:

1. Clone the repository
2. Install dependencies: yarn install
3. Build the project: yarn build
4. Copy the path of the dist/index.js file in the of the monday-api-mcp package.
5. Change the config to work locally

    "monday-api-mcp": {
      "command": "node",
      "args": [
        "<your_full_path_to_the_package>/dist/index.js",
        "--enable-dynamic-api-tools",
        "true"
      ],
      "env": {
        "MONDAY_TOKEN": "your_monday_api_token"
      }
    }

🤝 Contributing

We welcome contributions from the community! Whether it's fixing bugs, improving documentation, or adding new features, your help is appreciated.

1. Fork the repository
2. Create your feature branch: git checkout -b feature/amazing-feature
3. Commit your changes: git commit -m 'Add some amazing feature'
4. Push to the branch: git push origin feature/amazing-feature
5. Open a Pull Request

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

It is clarified that the server uses the monday.com API, which is subject to monday.com's Developer Terms

🚀 Quick Start: Hosted MCP (Recommended)

The fastest, most robust, and reliable way to connect to monday.com. Our hosted MCP service handles all the infrastructure for you - no local setup, automatic updates, and improved performance.

📚 Integration Guides

Get started with your favorite AI platform:

• Get Started Guide - First time using monday MCP?
• Claude Integration - Connect with Claude Desktop
• Cursor Integration - Integrate with Cursor IDE
• ChatGPT Integration - Connect with ChatGPT
• MS Copilot Integration - Integrate with Microsoft Copilot Studio
• Mistral Integration - Connect with Mistral AI's le Chat
• Ready-to-Use Prompts - Example prompts to get started

Quick Setup with Hosted MCP

For Cursor

Simply add this to your MCP settings:

{
  "mcpServers": {
    "monday-mcp": {
      "url": "https://mcp.monday.com/mcp"
    }
  }
}

Why Use the Hosted MCP?

• ✅ No local installation - Works immediately without setup
• ✅ Automatic updates - Always get the latest features
• ✅ Better performance - Optimized infrastructure
• ✅ OAuth authentication - Secure token management
• ✅ Workspace controls - Limit access to specific workspaces
• ✅ Higher reliability - Enterprise-grade uptime

When to Use This Repository Instead

You might want to run the MCP locally or use the agent toolkit if you need to:

• 🔧 Customize the MCP server - Modify the source code for specific needs
• 🛠️ Build custom agents - Use the agent toolkit for OpenAI or custom implementations
• 🔌 Work offline - Develop without internet connectivity
• 🧪 Contribute to development - Help improve the MCP server or toolkit

🏁 Local Installation Guide

Step 1: Create a monday.com Account

If you don't already have a monday.com account:

1. Go to monday.com and sign up for an account
2. Create your first workspace and board to get started

Step 2: Generate an API Token

To interact with monday.com's API, you'll need an API token:

1. Log in to your monday.com account
2. Click on your avatar in the bottom-left corner
3. Select "Developers"
4. Click "My access tokens" on the left menu
5. Copy your personal access token

Step 3: Configure Your MCP Client

For Claude Desktop

1. Open Claude Desktop
2. Go to Settings → MCP Servers
3. Add a new server with this configuration:

{
  "mcpServers": {
    "monday-api-mcp": {
      "command": "npx",
      "args": [
        "@mondaydotcomorg/monday-api-mcp@latest"
      ],
      "env": {
        "MONDAY_TOKEN": "your_monday_api_token"
      }
    }
  }
}

For Gemini CLI

To get started with Gemini CLI, you can use the official Gemini CLI extension for monday.com.

The Gemini CLI extension bundles the monday.com MCP server with a context file and custom commands that teaches Gemini how to use the monday.com tools for powerful workflows.

To install the extension run the following command in your terminal:

gemini extensions install https://github.com/mondaycom/mcp

If you prefer to use the MCP server directly without the extension, you can add it with this command:

gemini mcp add -t http monday https://mcp.monday.com/mcp

Once you have either the extension installed or the MCP server added, start Gemini CLI by running:

gemini

Then, authenticate with your monday.com account by running the following command inside Gemini CLI:

/mcp auth monday

This will open a browser window to complete the authentication process. After authenticating, all the monday.com tools and custom commands will be available.

A few custom command to try out for the extension:

• /monday:create-item create item in board 123 for "Update the UI"
• /monday:sprint-summary sprint summary for sprint 853

For Cursor or Other MCP Clients (Local Setup)

Add to your settings:

{
  "mcpServers": {
    "monday-api-mcp": {
      "command": "npx",
      "args": [
        "@mondaydotcomorg/monday-api-mcp@latest"
      ],
      "env": {
        "MONDAY_TOKEN": "your_monday_api_token"
      }
    }
  }
}

Step 5: Test Your Integration

1. Ask Claude or your AI assistant a question like:

   • "What items do I have in board 123?"
   • "Can you create a board to manage my project?"

2. Your assistant should now be able to interact with your monday.com account!

⚙️ Advanced Hosted MCP Configuration

Using Authorization Headers

To specify a custom authorization header and API version with the hosted MCP:

{
  "mcpServers": {
    "monday-api-mcp-hosted": {
      "command": "npx",
      "args": [
        "-p",
        "node@20",
        "mcp-remote",
        "https://mcp.monday.com/mcp",
        "--header",
        "Authorization:${AUTH_HEADER}"
      ],
      "env": {
        "AUTH_HEADER": "Bearer <your_token>"
      }
    }
  }
}

Specifying API Version

You can specify the API version you want to use with the --header parameter:

{
  "mcpServers": {
    "monday-api-mcp-hosted": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://mcp.monday.com/mcp",
        "--header",
        "Api-Version:${API_VERSION}"
      ],
      "env": {
        "API_VERSION": "2025-07"
      }
    }
  }
}

Installing the Monday MCP App

For OAuth authentication and workspace controls, install the Monday MCP app from the marketplace:

1. Visit monday MCP app in the marketplace
2. Click "Install" and follow the instructions to add it to your account

🖥️ MCP Server Configuration

📋 Prerequisites

Before using these tools, make sure you have:

1. Node.js v20 or higher installed
2. NPM v5.2.0 or higher installed
3. A monday.com API token