Monday.com

This is monday.com’s official MCP Server that lets AI assistants like Claude interact directly with your monday.com workspace.

This open-source implementation of MCP provides structured access to boards, items, users, and workflows through both predefined operations and dynamic GraphQL capabilities.

Features

  • 🔌 Direct monday.com API Integration – Secure connection using your existing API tokens or OAuth.
  • 📊 Complete Board Management – Create boards, add items, modify columns, and manage groups.
  • 🔄 Real-time Workflow Operations – Update item statuses, move between groups, and track progress.
  • 🎯 Dynamic GraphQL Tools – Beta feature for executing custom queries against monday.com’s full API schema.
  • 🔒 Multiple Deployment Options – Choose between local server installation or hosted service.
  • 👥 Team Collaboration Support – Access user information and team structures.
  • 📝 Form Creation & Management – Build and manage monday.com WorkForms programmatically.
  • Read-Only Mode – Safe data retrieval without modification capabilities.

Use Cases

  • Hands-Free Project Management: You could build an assistant that lets you manage your projects through conversation. Instead of manually clicking through the interface to create a task, you could just say, “Create a task to draft the Q4 report on the marketing board and assign it to Alex.” This removes the friction of context-switching and manual data entry.
  • Intelligent Data Retrieval: Sometimes you need a specific piece of information that isn’t in a standard dashboard. You could ask an agent, “How many tasks in the ‘Stuck’ group across all active projects are assigned to the design team?” The agent can then query the data and give you a direct answer.
  • Automated Board and Workflow Creation: For repetitive project setups, an agent can be a huge help. You could have it create a new board from a specific template, add the relevant team members, and populate the first few tasks based on a project brief.

Installation

You have two main options: running it locally or using the hosted service.

Option 1: Running the MCP Server Locally

1. Get Your Monday.com API Token

  • Log in to your monday.com account.
  • Click your avatar (bottom-left) and go to the “Developers” section.
  • Find “My access tokens” and copy your personal access token.

2. Configure Your MCP Client:

For Claude Desktop

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

For Cursor

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

3. Ask your AI assistant a question related to your monday.com account, like, “What are the items on board 12345?” It should now be able to connect and fetch the information.

Option 2: Using the Hosted MCP Service

This is the easier route. You don’t manage the server, and authentication is handled through OAuth.

1. Go to the monday MCP app in the marketplace and install it in your account.

2. Configure Your Client:

{
  "mcpServers": {
    "monday-api-mcp-hosted": {            "command": "npx",
      "args": [
        "mcp-remote",
        "https://mcp.monday.com/sse"
      ]
    }
  }
}

Server Configuration

You can modify the server’s behavior with these command-line arguments:

  • --token, -t: Your monday.com API token. (Required for local server)
  • --version, -v: The monday.com API version to use. Defaults to current.
  • --read-only, -ro: Restricts the agent to only reading data. It cannot create, update, or delete anything. Defaults to false.
  • --enable-dynamic-api-tools, -edat: Enables the beta Dynamic API Tools for full GraphQL access. Can be set to true or only. Defaults to false.

Available Tools

Item Operations

  • create_item: Creates a new item in a specified board.
  • delete_item: Permanently removes an item from a board.
  • get_board_items_by_name: Searches for items on a board by their name or a search term.
  • create_update: Adds a comment or update to a specific item.
  • change_item_column_values: Modifies the column values for an existing item.
  • move_item_to_group: Moves an item into a different group on the same board.

Board Operations

  • create_board: Creates a new board with a specified set of columns.
  • get_board_schema: Fetches the structure of a board, including its columns and groups.
  • create_group: Adds a new group to a board.
  • create_column: Adds a new column to an existing board.
  • delete_column: Removes a column from a board.

Account Operations

  • list_users_and_teams: Retrieves details for users or teams by their ID, name, or by searching the account.

WorkForms Operations

  • create_form: Creates a new monday.com form.
  • get_form: Retrieves a form using its token.

Dynamic API Tools (Beta)

  • all_monday_api: Generates and executes any GraphQL query or mutation, providing full access to the monday.com API.
  • get_graphql_schema: Fetches the entire monday.com GraphQL schema so the agent can understand all available data and operations.
  • get_type_details: Retrieves detailed information about specific GraphQL types within the schema.

FAQs

Q: What is the main difference between the local server and the hosted service?
A: The local server runs on your own machine, which means you are responsible for keeping it running. The hosted service is managed by monday.com, uses a more secure OAuth flow for authentication instead of a static token, and updates automatically. The hosted option is simpler for most people.

Q: When should I use the Dynamic API Tools?
A: Use them when the standard, pre-built tools aren’t enough. If you need to perform a very specific or complex GraphQL query, interact with advanced monday.com features, or perform large batch operations, the Dynamic API Tools give your agent the power to do that. It’s an advanced feature, so stick with the standard tools unless you have a specific need.

Q: How does authentication work with the hosted service?
A: The hosted service uses OAuth flow through the monday.com marketplace app. You install the MCP app once, and it manages authentication automatically without exposing API tokens in your configuration.

Q: Can I restrict the MCP server to specific workspaces?
A: Yes, the hosted service allows workspace-level permissions. When installing the Monday MCP app from the marketplace, you can choose which workspaces it can access.

Q: What’s the difference between standard tools and dynamic API tools?
A: Standard tools cover common operations like creating items and boards. Dynamic API tools provide raw GraphQL access for complex queries, batch operations, and accessing newer API features not yet covered by standard tools.

Q: Is my data secure when using this MCP server?
A: The server only communicates with monday.com’s official API using your token. For additional security, use read-only mode when you only need data retrieval, and regularly rotate your API tokens.

Q: Can I use this with multiple monday.com accounts?
A: Each MCP server instance connects to one monday.com account. For multiple accounts, you’d run separate server instances with different configurations.

Latest MCP Servers

CVE

An MCP Server that connects Claude to 27 security tools for CVE triage, EPSS checks, KEV status, exploit lookup, and package scanning.

WebMCP

webmcp is an MCP server that connects MCP clients to web search, page fetching, and local LLM-based extraction. It’s ideal…

Google Meta Ads GA4

An MCP server that connects AI assistants to Google Ads, Meta Ads, and GA4 for reporting, edits, and cross-platform analysis.

View More MCP Servers >>

Featured MCP Servers

Notion

Notion's official MCP Server allows you to interact with Notion workspaces through the Notion API.

Claude Peers

An MCP server that enables Claude Code instances to discover each other and exchange messages instantly via a local broker daemon with SQLite persistence.

Excalidraw

Excalidraw's official MCP server that streams interactive hand-drawn diagrams to Claude, ChatGPT, and VS Code with smooth camera control and fullscreen editing.

More Featured MCP Servers >>

FAQs

Q: What exactly is the Model Context Protocol (MCP)?

A: MCP is an open standard, like a common language, that lets AI applications (clients) and external data sources or tools (servers) talk to each other. It helps AI models get the context (data, instructions, tools) they need from outside systems to give more accurate and relevant responses. Think of it as a universal adapter for AI connections.

Q: How is MCP different from OpenAI's function calling or plugins?

A: While OpenAI's tools allow models to use specific external functions, MCP is a broader, open standard. It covers not just tool use, but also providing structured data (Resources) and instruction templates (Prompts) as context. Being an open standard means it's not tied to one company's models or platform. OpenAI has even started adopting MCP in its Agents SDK.

Q: Can I use MCP with frameworks like LangChain?

A: Yes, MCP is designed to complement frameworks like LangChain or LlamaIndex. Instead of relying solely on custom connectors within these frameworks, you can use MCP as a standardized bridge to connect to various tools and data sources. There's potential for interoperability, like converting MCP tools into LangChain tools.

Q: Why was MCP created? What problem does it solve?

A: It was created because large language models often lack real-time information and connecting them to external data/tools required custom, complex integrations for each pair. MCP solves this by providing a standard way to connect, reducing development time, complexity, and cost, and enabling better interoperability between different AI models and tools.

Q: Is MCP secure? What are the main risks?

A: Security is a major consideration. While MCP includes principles like user consent and control, risks exist. These include potential server compromises leading to token theft, indirect prompt injection attacks, excessive permissions, context data leakage, session hijacking, and vulnerabilities in server implementations. Implementing robust security measures like OAuth 2.1, TLS, strict permissions, and monitoring is crucial.

Q: Who is behind MCP?

A: MCP was initially developed and open-sourced by Anthropic. However, it's an open standard with active contributions from the community, including companies like Microsoft and VMware Tanzu who maintain official SDKs.

Get the latest & top AI tools sent directly to your email.

Subscribe now to explore the latest & top AI tools and resources, all in one convenient newsletter. No spam, we promise!