Connector guide6-minute read20 MCP tools7 languages

How to Connect monday.com to ChatGPT via MCP

Let your AI work in monday.com: find boards and items, read column values and comments, create items, update statuses, dates and owners, and post updates. One account, with your personal API token.

HCBy HelpCode teamUpdated 6 min read Open-source on GitHub

No credit card · 7-day trial · Self-host alternative available

monday.com

monday.com

Let your AI work in monday.com: find boards and items, read column values and comments, create items, update statuses, dates and owners, and post updates. One account, with your personal API token.

tools

20

Region

INTL

Category

Project Management

Authentication

API Key

Required env vars

MONDAY_API_TOKEN
Install in one click on Cloud

7-day free trial · No credit card

  • 7-day free trial
    No credit card required
  • GDPR & SOC 2 ready
    EU data residency, audit logs
  • Open-source on GitHub
    Open source · AGPL-3.0
  • Works with ChatGPT, Claude, Gemini
    Any MCP-compatible client

Skip the install. Get this working in under 2 minutes.

Start a free trial on cloud.anythingmcp.com, add the monday.com in one click, then point your AI client (Claude, ChatGPT, Copilot or Cursor) at the generated MCP endpoint. No Docker, no git clone, zero engineering experience required.

Start free trial

Summary

Let your AI work in monday.com: find boards and items, read column values and comments, create items, update statuses, dates and owners, and post updates. One account, with your personal API token.

Try asking

Example prompts for monday.com

Click any prompt to copy it. Paste into Claude, ChatGPT, Cursor, Gemini, Copilot or OpenClaw to run it against this connector.

monday.com · live via MCP
Share
Opus 4.7

Claude is AI and can make mistakes. Please double-check responses.

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → monday.com, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

monday.com + ChatGPT

Let your AI work in monday.com: find boards and items, read column values and comments, create items, update statuses, dates and owners, and post updates. One account, with your personal API token.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

MONDAY_API_TOKEN

Step 1 — Get credentials

  1. In monday.com, click your profile picture (top right) and choose Developers. The Developer Center opens in a new tab.
  2. Open API token (called My access tokens in older menus), click Show and copy the token. Account admins also find it under Administration → Connections → Personal API token.
  3. Paste the token into MONDAY_API_TOKEN, without the word Bearer, then install the connector.
  4. Start with monday_get_me: it shows which user and which account the token acts as.

Whose token: the token acts as the user it belongs to, with all of that user's permissions, so the AI sees and changes exactly what that user can in monday.com. Use the token of an admin or member; guests and viewers have no personal token. Regenerating the token in the same place makes the old one stop working immediately.

Read-only setup: personal tokens cannot be limited to reading. Give the token's user access only to the boards the AI needs, and disable monday_create_item, monday_change_column_values, monday_move_item_to_group, monday_create_group, monday_create_update and the generic monday_graphql_mutation, which can run any change the API allows.

Switched off at install: monday_archive_item. Turn it on only if the AI should remove items. Archived items leave the board and can be restored from the board's archive.

Beyond the ready-made tools: monday.com has a GraphQL API. monday_graphql_schema and monday_graphql_query let the AI read anything else it offers, such as docs, dashboards or activity logs.

Limits: personal tokens share a budget of complexity points per minute, and every account has a daily call limit that depends on the plan: 1,000 calls on Free, Basic and Standard, 10,000 on Pro and 25,000 on Enterprise. Over a limit, the error says how many seconds to wait.

Common errors: Not Authenticated or 401 means the token is wrong or was regenerated. UserUnauthorizedException means the token's user has no access to that board or item. InvalidColumnIdException or ColumnValueException means a wrong column id or value format: the AI reads the board's columns and status labels with monday_get_board first. ComplexityException, DAILY_LIMIT_EXCEEDED or Minute limit rate exceeded means a limit was reached: wait and try again with smaller pages.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in ChatGPT

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

ChatGPT connects to MCP servers as custom apps in developer mode, available on paid plans (not on Free). On Business and Enterprise workspaces an admin may have to allow it first.

  1. In ChatGPT, open Settings → Security and login and turn on Developer mode.
  2. Go to chatgpt.com/plugins and click +.
  3. Enter a name and a short description, e.g. Name: monday.com.
  4. Under Connection, enter the MCP server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID and create the connection.
  5. When ChatGPT asks, sign in to AnythingMCP (OAuth) and allow access.

Available tools

ToolWhat it does
monday_get_meCheck the token and return who it acts as: user id, name, email, title, time zone, and the account's id, name, slug and plan tier
monday_list_workspacesList the workspaces the user can see: id, name, kind (open, closed, template) and description, a page at a time
monday_list_boardsList boards the user can access: id, name, description, kind (public, private, share), state, workspace id, item count, last update and URL
monday_get_boardGet one board's structure: name, workspace, owners, item count, its groups (id, title, color, position) and its columns (id, title, type…
monday_get_items_pageRead a board's items with their column values (id, type, text and raw JSON value), optionally filtered and sorted with query_params, up to…
monday_next_items_pageFetch the next page of items for a cursor returned by monday_get_items_page (or by a previous call of this tool), with the same item fields
monday_get_itemsGet items by id, from any board: name, board, group, state, creator, timestamps, URL, all column values and their subitems (id and name)
monday_create_itemCreate an item on a board, optionally in a group and with column values
monday_change_column_valuesChange one or more column values of an item, including its name (column id "name")
monday_move_item_to_groupMove an item to another group of the same board
monday_create_groupAdd a group (section) to a board, at the top by default or next to another group
monday_list_updatesRead the updates (comments) on an item, newest first, with their replies: id, plain text, HTML body, creator and time
monday_create_updatePost an update (comment) on an item, or a reply to an update with parent_id
monday_list_usersList the account's users: id, name, email, title, kind (admin, member, guest, view_only), status and time zone
monday_archive_itemArchive an item and its subitems: it leaves the board and can be restored from the board's archive
monday_graphql_schema_urlReturn the URL of the GraphQL schema (SDL)
monday_graphql_schemaFetch the GraphQL schema: a summary, one type, a search slice or the full SDL
monday_graphql_queryRun an arbitrary GraphQL query
monday_graphql_mutationRun an arbitrary GraphQL mutation
monday_graphql_subscriptionRun an arbitrary GraphQL subscription (if the API supports it)

Example prompts

  • "What's on the Marketing board that is due this week and not Done yet?"
  • "Create an item 'Prepare the Q4 newsletter' on the Content Plan board, assign it to Laura and set the date to 15 November."
  • "Set the status of 'Website relaunch' to Working on it and post an update saying the design was approved."
  • "Read the latest updates on the item 'Client onboarding Acme' and summarize what is still open."

FAQ

Does the free ChatGPT plan work with custom MCP connectors? No. Custom MCP connections need developer mode, which is only on paid plans.

Next steps

Was this guide helpful?

Your monday.com agent is one click away.

Install the connector, paste the key, prompt ChatGPT. Free for 7 days, no credit card.

Related guides

Connectors

How to Connect monday.com to Claude via MCP

Let your AI work in monday.com: find boards and items, read column values and comments, create items, update statuses, dates and owners, and post updates. One account, with your personal API token.

Connectors

How to Connect monday.com to Cursor via MCP

Let your AI work in monday.com: find boards and items, read column values and comments, create items, update statuses, dates and owners, and post updates. One account, with your personal API token.

Connectors

How to Connect monday.com to Gemini via MCP

Let your AI work in monday.com: find boards and items, read column values and comments, create items, update statuses, dates and owners, and post updates. One account, with your personal API token.

Connectors

How to Connect monday.com to Meta Muse via MCP

Let your AI work in monday.com: find boards and items, read column values and comments, create items, update statuses, dates and owners, and post updates. One account, with your personal API token.

Connectors

monday.com to MCP: Drive monday.com from any AI Agent

Let your AI work in monday.com: find boards and items, read column values and comments, create items, update statuses, dates and owners, and post updates. One account, with your personal API token.

Connectors

How to Connect Canva to ChatGPT via MCP

Let your AI work in Canva: find and read designs, create new ones, export them to PDF, PNG, PowerPoint or video with download links, organise folders, upload images from a link, read brand templates and comment on designs.