mcp

The monday.com MCP server provided by this repository exposes the monday.com API as an MCP-compatible service. It enables AI agents and automation tools to securely access monday.com data, perform actions such as creating items, updating boards, and reading workspace information, all within the MCP framework. You can integrate this server with various MCP clients and agent toolkits (like the Agent Toolkit or Gemini/CUDA-based workflows) to enable natural-language driven interactions with your monday.com workspace. Typical usage involves configuring an MCP client to point at this server and supplying a Monday API token via the MONDAY_TOKEN environment variable to authorize requests.

To get started, configure your MCP client with the server entry (for example, in Claude Desktop or Cursor-based setups) using the provided npx-based command. Provide your monday.com API token as an environment variable if required by your client setup. Once connected, you can invoke monday.com tools through your AI agent, such as querying board items, creating items, or updating statuses, leveraging the MCP interface to ensure structured, policy-compliant interactions.

Prerequisites:

• Node.js v20 or newer installed on your machine
• npm (comes with Node.js)

Local setup (recommended via MCP config):

1. Ensure you have a monday.com account and generate a personal access token (MONDAY_TOKEN) with the necessary scopes for reads/writes to boards and items.
2. Install and run the MCP server using npx as described in the config:

# Run directly via npx (no local install required)
npx @mondaydotcomorg/monday-api-mcp@latest

3. Provide your MONDAY_TOKEN in the environment where you run the MCP client or configure it in your MCP settings as shown:

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

4. Verify connectivity by testing a simple read operation (e.g., list items on a board) through your MCP client or CLI integration.

Optional: If you prefer a more persistent setup, you can install the package locally in a project and run it from a script, then reference the local path in your MCP configuration.

Token management: MONDAY_TOKEN is required to authorize API calls to monday.com. Keep tokens secret and rotate them periodically. Some environments may require additional OAuth scopes depending on the actions you perform (read boards, write items, manage users). If you encounter connectivity issues, ensure your network permits outbound requests to monday.com's API endpoints and that the token is valid.

Environment and compatibility: This MCP server is designed to work with MCP clients such as Claude Desktop, Gemini CLI, Cursor, or other MCP-enabled tools. When using hosted vs. local setups, consider latency and reliability requirements for production use. If you customize or extend the server, follow MCP best practices for context handling and rate-limiting to avoid throttling by monday.com APIs.