Monday.com logo

Monday.com

Connect AI clients to monday.com boards and work data through hosted or locally run MCP tools.

Install Monday.com

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "monday-com": {
      "command": "npx",
      "args": [
        "-y",
        "@mondaydotcomorg/monday-api-mcp@latest"
      ],
      "env": {
        "MONDAY_TOKEN": "YOUR_VALUE_HERE",
        "AUTH_HEADER": "YOUR_VALUE_HERE",
        "API_VERSION": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

npx -y @mondaydotcomorg/monday-api-mcp@latest

No response to initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked .

Overview

The monday.com MCP server connects AI clients to the monday.com API, allowing agents to read structured work data and take actions such as creating boards or items. It is available as a hosted MCP endpoint or as a local Node.js package configured with an API token. Use it when an assistant needs to query or update monday.com workspaces, boards, projects, or tasks. The repository also includes an agent toolkit for building OpenAI- or MCP-based agents.

Use cases

  • Query items on a monday.com board
  • Create boards for project management
  • Add items to existing boards
  • Build custom agents around monday.com data
  • Generate sprint summaries with Gemini CLI

Key features

  • Hosted MCP endpoint
  • Local npm-based MCP server
  • monday.com API access
  • Board and item actions
  • Gemini CLI extension
  • OpenAI and MCP agent toolkit

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked

Recent health check succeeded.

27/28 checks healthy over the last 95d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 7d ago via OSV.dev · @mondaydotcomorg/monday-api-mcp@latest (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars437Stargazers on the source repository.
npm downloads11kPackage downloads in the last 30 days.
Last commit1d agoMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.
Directory activity3 viewsConfig copies, upvotes, and views on AllMCPs.

How Monday.com works

What monday.com MCP server does

The monday.com MCP server gives AI assistants an MCP interface to monday.com, a work operating system used for projects, processes, tasks, collaboration, and reporting. Agents can access structured workspace data and perform actions through the monday.com API rather than requiring a separate custom integration for each assistant.

The repository contains the @mondaydotcomorg/monday-api-mcp package, which runs the API-facing MCP server. It also includes @mondaydotcomorg/agent-toolkit for developers building agents that use monday.com through OpenAI or MCP implementations. The documented examples include asking for items on a board, creating a board, and creating an item with the Gemini CLI extension.

How it works

Two deployment paths are documented. The hosted service is available at https://mcp.monday.com/mcp and can be added to compatible clients as an MCP URL. Hosted access uses OAuth authentication and is managed by monday.com, so clients do not need a local package installation. The hosted service also supports workspace access controls and an optional API-version header.

For local use, an MCP client launches the npm package with npx. The process communicates with monday.com using a personal API token supplied through the environment. This option is intended for source customization, custom agent development, offline development, or contribution work.

The monday.com MCP server is also available through an official Gemini CLI extension. The extension adds the server together with context instructions and custom commands, while Gemini CLI can alternatively connect directly to the hosted endpoint.

Setup and configuration

The simplest hosted configuration points an MCP client at https://mcp.monday.com/mcp. Cursor’s documented configuration uses this URL directly. Gemini CLI can install the repository extension or add the hosted server with gemini mcp add, then authenticate with /mcp auth monday.

A local setup requires a monday.com account, a workspace and board, Node.js 20 or later, and a personal access token. Configure the client to run npx @mondaydotcomorg/monday-api-mcp@latest and provide the token as MONDAY_TOKEN.

Hosted connections can also be configured through mcp-remote with an Authorization header. An Api-Version header may be supplied when a specific monday.com API version is needed.

Tools and capabilities

The available interface is designed for agents that need to work with monday.com data and workflows. Supported use described in the repository includes:

  • Reading items from a specified board.
  • Creating boards for project or process management.
  • Creating items on a board.
  • Accessing monday.com’s structured work data through MCP tools.
  • Building custom agent workflows with the agent toolkit.
  • Using Gemini CLI commands such as board-item creation and sprint summaries through the extension.

The exact tool catalog is provided by the running package or hosted service and may change as the service is updated.

Limitations and notes

The hosted and local configurations are different deployment choices. Hosted MCP avoids local installation and receives service updates automatically, while local execution gives developers access to the repository and package for customization. Local API access depends on a valid monday.com token and network access to the monday.com API unless the surrounding development workflow is otherwise configured.

The repository documents integrations for Claude Desktop, Cursor, Gemini CLI, ChatGPT, Microsoft Copilot Studio, and Mistral’s le Chat through separate guides or extension support. Only clients with MCP support and an appropriate connection method can use the server directly. Keep API tokens and authorization values in client configuration or environment management rather than exposing them in prompts.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Monday.com

monday.com is an MCP server that connects AI clients to the monday.com API and exposes tools for reading and changing workspace data, including boards, items, and project workflows. It supports local stdio execution through npm and a hosted MCP endpoint, with authentication handled by a monday.com token or hosted OAuth.

Install the local server by configuring your MCP client to run `npx @mondaydotcomorg/monday-api-mcp@latest` and setting `MONDAY_TOKEN`. You can instead use the hosted endpoint at `https://mcp.monday.com/mcp`, which avoids local installation and uses hosted authentication.

Yes, monday.com works with Cursor through either the hosted MCP URL or the local npm server. Add `https://mcp.monday.com/mcp` to Cursor’s MCP settings for hosted access, or configure Cursor to launch the package with `MONDAY_TOKEN`.

Authenticate local connections with a monday.com personal API token stored in `MONDAY_TOKEN`. Hosted connections use OAuth, and the documentation also shows an optional `Authorization` header configuration for clients using `mcp-remote`.

Yes, Gemini CLI supports monday.com through an official extension or a direct hosted MCP connection. Install the extension from the repository, or run `gemini mcp add -t http monday https://mcp.monday.com/mcp`, then authenticate with `/mcp auth monday`.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewMonday.com AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/monday-com?style=directory)](https://allmcps.com/mcp/monday-com)
HTML Embed
<a href="https://allmcps.com/mcp/monday-com"><img src="https://allmcps.com/api/badge/monday-com?style=directory" alt="Monday.com on AllMCPs" /></a>