mcp

Name: mcp
Author: mondaycom

Issues

Enable AI agents to work reliably - giving them secure access to structured data, tools to take action, and the context needed to make smart decisions.

417stars

88forks

TypeScript

Installation

# Add to your Claude Code skills
git clone https://github.com/mondaycom/mcp

Getting Started

Guides for using ai agents skills like mcp.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

Security ReportIssues

Last scanned: 5/22/2026

{
  "issues": [
    {
      "type": "npm-audit",
      "message": "@ardatan/relay-compiler: Vulnerability found",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "@modelcontextprotocol/sdk: Anthropic's MCP TypeScript SDK has a ReDoS vulnerability",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "@mondaydotcomorg/atp-mcp-adapter: Vulnerability found",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "@mondaydotcomorg/atp-server: Vulnerability found",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "@opentelemetry/auto-instrumentations-node: Vulnerability found",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "@opentelemetry/exporter-prometheus: Prometheus exporter process crash via malformed HTTP request",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "@opentelemetry/sdk-node: Vulnerability found",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "@protobufjs/utf8: protobufjs has overlong UTF-8 decoding",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "@rollup/plugin-terser: Vulnerability found",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "@xmldom/xmldom: xmldom: Uncontrolled recursion in XML serialization leads to DoS",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "ajv: ajv has ReDoS when using `$data` option",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "axios: Axios is vulnerable to DoS attack through lack of data size check",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "body-parser: body-parser is vulnerable to denial of service when url encoding is used",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "brace-expansion: brace-expansion Regular Expression Denial of Service vulnerability",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "diff: jsdiff has a Denial of Service vulnerability in parsePatch and applyPatch",
      "severity": "low"
    },
    {
      "type": "npm-audit",
      "message": "exceljs: Vulnerability found",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "external-editor: Vulnerability found",
      "severity": "low"
    },
    {
      "type": "npm-audit",
      "message": "flatted: flatted vulnerable to unbounded recursion DoS in parse() revive phase",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "follow-redirects: follow-redirects leaks Custom Authentication Headers to Cross-Domain Redirect Targets",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "form-data: form-data uses unsafe random function in form-data for choosing boundary",
      "severity": "critical"
    },
    {
      "type": "npm-audit",
      "message": "gaxios: Vulnerability found",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "immutable: Immutable is vulnerable to Prototype Pollution",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "inquirer: Vulnerability found",
      "severity": "low"
    },
    {
      "type": "npm-audit",
      "message": "js-yaml: js-yaml has prototype pollution in merge (<<)",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "jws: auth0/node-jws Improperly Verifies HMAC Signature",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "lodash: Lodash has Prototype Pollution Vulnerability in `_.unset` and `_.omit` functions",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "minimatch: minimatch has a ReDoS via repeated wildcards with non-matching literal in pattern",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "path-to-regexp: path-to-regexp vulnerable to Denial of Service via sequential optional groups",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "picomatch: Picomatch: Method Injection in POSIX Character Classes causes incorrect Glob Matching",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "protobufjs: Arbitrary code execution in protobufjs",
      "severity": "critical"
    },
    {
      "type": "npm-audit",
      "message": "qs: qs's arrayLimit bypass in comma parsing allows denial of service",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "rollup: Rollup 4 has Arbitrary File Write via Path Traversal",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "serialize-javascript: Serialize JavaScript is Vulnerable to RCE via RegExp.flags and Date.prototype.toISOString()",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "tmp: tmp allows arbitrary temporary file / directory write via symbolic link `dir` parameter",
      "severity": "low"
    },
    {
      "type": "npm-audit",
      "message": "turbo: Trubo: Login callback CSRF/session fixation",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "undici: Undici has an unbounded decompression chain in HTTP responses on Node.js Fetch API via Content-Encoding leads to resource exhaustion",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "uuid: uuid: Missing buffer bounds check in v3/v5/v6 when buf is provided",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "ws: ws: Uninitialized memory disclosure",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "yaml: yaml is vulnerable to Stack Overflow via deeply nested YAML collections",
      "severity": "medium"
    }
  ],
  "status": "FAILED",
  "scannedAt": "2026-05-22T07:45:56.494Z",
  "semgrepRan": false,
  "npmAuditRan": true,
  "pipAuditRan": true
}

README.md

Frequently Asked Questions

What is mcp?

mcp is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by mondaycom. Enable AI agents to work reliably - giving them secure access to structured data, tools to take action, and the context needed to make smart decisions. It has 417 GitHub stars.

Is mcp safe to use?

mcp failed SkillsLLM's automated security scan, which flagged one or more high-severity issues. Review the Security Report section carefully before using it.

How do I install mcp?

Clone the repository with "git clone https://github.com/mondaycom/mcp" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is mcp written in?

mcp is primarily written in TypeScript. It is open-source under mondaycom on GitHub, so you can review or fork the full source.

Are there alternatives to mcp?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh mcp against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

superpowers

by obra

An agentic skills framework & software development methodology that works.

234,966

dockershrink solon-ai

🚀 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.

🚀 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:

Go to monday.com and sign up for an account
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:

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

Step 3: Configure Your MCP Client

For Claude Desktop

Open Claude Desktop
Go to Settings → MCP Servers
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

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?"
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:

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

🧰 Available Tools

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

Category	Tool	Description
Item Operations	create_item	Create a new item in a monday.com board with specified column values
	delete_item	Delete an item from a board permanently
	get_board_items_by_name	Search for items by board ID and term/name
	create_update	Add an update/comment to a specific item
	change_item_column_values	Modify the column values of an existing item
	move_item_to_group	Move an item to a different group within the same board
Board Operations	create_board	Create a new monday.com board wit