Skip to content

MCP server

monday.com MCP server

monday.com's official MCP server lets AI read boards and items, create and update items and columns, post updates and use the full monday API.

At a glance

Maintained by
monday.com
Tools exposed
10 listed below
Reviewed
September 24, 2026

Why it matters

What it does and why it matters

monday.com is a work management platform used for projects, sales pipelines, hiring and more. Its official MCP server lets an assistant find items, read board structures, create items, change column values, move items between groups, post updates, create boards, list users and teams, call the full monday API and delete items.

Because monday boards are used for so many kinds of work, one server can support project updates, simple CRM tasks and request tracking.

The server includes delete and a general API tool, which together give broad control. We connect with a user limited to the relevant boards, keep deletes behind approval and prefer the specific tools over the general API tool where possible.

Use cases

Best business use cases

Board updates

Update item status and columns from a description.

Updates

Post progress updates on items.

Simple CRM

Manage leads on a monday board. See lead qualification.

Request intake

Create items from incoming requests.

Board summaries

Summarize a board by group and status.

Tools

Available tools

Tool names as published by the maintainer at review time. Versions change, so check the repository for the current list.

Read and write: Read and write for boards, items, columns, updates and forms, including delete.

  • get_board_items_by_name

    Searches items on a board by name.

  • create_item

    Creates an item with column values.

  • change_item_column_values

    Changes column values on an item.

  • move_item_to_group

    Moves an item to another group.

  • create_update

    Adds an update (comment) to an item.

  • create_board

    Creates a board.

  • get_board_schema

    Gets a board's columns and groups.

  • list_users_and_teams

    Looks up users and teams.

  • all_monday_api

    Runs any GraphQL query or mutation (beta).

  • delete_item

    Deletes an item permanently.

Workflows

Example workflows

Request intake

  1. 1

    A request arrives by email.

  2. 2

    The assistant creates an item on the requests board.

  3. 3

    It fills in type, priority and requester.

  4. 4

    It posts an update with details.

  5. 5

    The team picks it up.

Friday board summary

  1. 1

    Ask for a summary of the projects board.

  2. 2

    The assistant reads items by group.

  3. 3

    It lists what moved this week.

  4. 4

    It flags stuck items.

  5. 5

    It posts the summary as an update.

Prompts

Example prompts

  • “Create an item on the Requests board for this email and set priority to high.”

  • “Which items on the Projects board have been stuck for over a week?”

  • “Move all done items in Sprint 12 to the Completed group.”

Setup

Installation and configuration

Examples for Claude Desktop and Claude Code. Replace the placeholder values with your own keys, and store secrets outside version control.

Claude Desktop: claude_desktop_config.json

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

Claude Code: terminal

claude mcp add --transport http monday https://mcp.monday.com/mcp
  • Hosted server: https://mcp.monday.com/mcp.
  • Local server: npx @mondaydotcomorg/monday-api-mcp@latest.
  • Needs: Hosted: OAuth 2.1 (or Bearer personal API token). Local: MONDAY_TOKEN personal API token..

Security

Security considerations

  • Limit workspaces

    Connect with an account that sees only the workspaces or projects a task needs.

  • Mark AI-created items

    Use a label or naming rule so items created by the assistant are easy to spot and review.

  • Guard deletes

    Deletes and the general API tool need extra care. Keep deletes behind approval.

  • Untrusted text

    Task descriptions and comments can contain misleading text. Treat them as data.

Related servers

Servers that pair well with it

Asana

Asana's official MCP server lets AI search work, read and create tasks and projects, add comments and post project status updates.

ClickUp

ClickUp's official MCP server lets AI search the workspace, read and create tasks, track time, create docs and send chat messages.

Airtable

Airtable's official hosted MCP server lets AI list workspaces, create bases and read records, with wider read and write access to tables and automations.

Keep exploring

FAQ

Questions people ask us

Have a question that is not here? Ask us directly.

Start a project

Want this connected to your own systems? We build AI workflows with MCP.

Send a short brief. We reply with questions, a suggested plan and an estimate you can compare with other offers.

Your privacy choices

We use necessary storage to run this site. With your permission we also use Google Analytics to see which pages help people, and load maps from Google. You can change this at any time. Read the cookie policy.