# AI and monday.com.

URL: https://levystreet.com/integrations/monday/
Updated: 2026-10-19

An AI monday.com integration guide for NZ: AI credits, the GraphQL API, webhooks and Platform MCP, and a project status summary that cites its sources.

## Short answer

An AI monday.com integration connects a model to your boards through monday's own AI (sidekick, agents and AI blocks), its GraphQL API and webhooks, or the hosted Platform MCP server. For New Zealand teams the most useful first job is a weekly status summary across boards that links every claim to an item, with each project manager approving it before anyone else reads it.

- New work platform customers since 6 May 2026 must buy AI credits with their seats.
- AI blocks cost 8 credits per action; AI Notetaker costs 120 credits per meeting hour.
- The hosted Platform MCP server is free on all plans and uses each person's access.
- MCP calls count toward daily API limits: 1,000 on Standard, 10,000 on Pro.
- Failed webhook deliveries are retried once a minute for only 30 minutes.

## What monday AI does natively (October 2026)

monday's AI comes as monday sidekick (an assistant), monday agents, AI blocks, AI Notetaker, AI workflows and monday vibe, all paid for in AI credits. According to [monday's pricing article](https://support.monday.com/hc/en-us/articles/35277848309394-The-pricing-model-for-monday-AI-portfolio) (last modified 3 October 2026), customers who joined the work platform on or after 6 May 2026 must buy credits with their seats: at least 1,000 a month on Basic, 2,000 on Standard and 3,000 on Pro.

Typical consumption: sidekick uses about 10 to 150+ credits per message, agents about 10 to 250+ per task (a run can include several tasks), AI blocks 8 per action, and AI Notetaker 120 per meeting hour. Admins can watch usage and set limits under AI governance, with alerts at 80% and 100%. Seat prices on monday's pricing page are shown as "$" with no currency code and depend on the billing country, so confirm at checkout.

## Integration routes and when to use each

| Route | What it gives you | Use it when |
|---|---|---|
| sidekick, agents and AI blocks | Summaries and actions inside monday, billed in credits | Managers work in monday and credit costs are acceptable |
| GraphQL API | Boards, items, column values and updates; writes through mutations | You need cross-board or cross-system reporting with your own logic |
| Webhooks | 21 board events, such as `change_status_column_value` and `create_update`, with `value` and `previousValue` | You want to react when a status changes |
| Platform MCP server | 60+ tools at `mcp.monday.com/mcp`, free on all plans, per-user OAuth | People ask Claude, ChatGPT or Copilot Studio about their own boards |
| n8n, Make or Zapier | Prebuilt steps plus GraphQL calls | Simple notifications and hand-offs |

## Automation 1: a weekly portfolio status people can trust


- **Inputs**: Items from the active project boards (name, status, owner, due date) and updates posted in the last seven days, read through the API with a read-only token.
- **Deterministic step**: Code counts overdue items, status changes this week and items stuck for more than ten days. Numbers never come from the model.
- **Model step**: One paragraph per project, labelled On track, At risk or Off track only from the computed facts, with links to the items behind each claim.
- **Human approval**: Each project manager edits and approves their own paragraph.
- **Write-back**: The approved text is posted as an update on that project's row in a separate Portfolio board. No status column is changed.
- **Failure and recovery**: If the daily API limit is hit, the run resumes from its saved position the next day, and the summary names any boards it could not read.


This follows the reporting approach in our [AI reporting](/services/ai-reporting/) service and the lesson on [preparing management reports with AI](/learn/using-ai-to-prepare-management-reports/).

## Automation 2: blocker notes when an item turns "Stuck"


1. **Subscribe narrowly.** Create a `change_specific_column_value` webhook for the Status column only; the payload carries the new and previous value.
2. **Gather context.** Fetch the item, its recent updates and its linked items.
3. **Draft.** The model writes a short blocker note: what is blocked, who probably owns the fix, and the question that would unblock it.
4. **Approve.** The project manager sees the draft in Teams or Slack and posts, edits or discards it.
5. **Reconcile.** A nightly query catches status changes whose webhook was lost.


## Permissions and approval design

Run custom jobs through a dedicated app with only the scopes it needs; webhook management alone needs `webhooks:read` and `webhooks:write`. App tokens get separate read and write complexity budgets of 5M points a minute, while personal tokens share 10M. For MCP, each user authorises individually and sees only their own data, admins control connections under Admin, Permissions, AI Connectors, and monday's help centre recommends reviewing AI-suggested changes before they apply. Our [MCP guide](/engineering/mcp-for-business-systems/) covers putting your own approval layer in front.

Updates often mention clients and staff. Do not let a summary rate individuals: under the Privacy Act 2020, IPP 8 requires reasonable steps to check information is accurate before you use it.

## Costs and limits (as listed 19 October 2026)

- **Daily API calls**: 1,000 on Free, Basic and Standard, 10,000 on Pro and 25,000 on Enterprise, reset at midnight UTC, which is 1 pm in New Zealand during daylight saving. MCP calls count.
- **Complexity**: a single query can cost at most 5M points.
- **Worked example**: an AI block run over 400 items every week uses about 12,800 credits a month (400 × 8 × 4), well above Standard's 2,000 minimum. A custom weekly summary of ten projects at 8,000 input and 400 output tokens each on Claude Sonnet 5.5 costs about US$0.20 a run.

## Where it goes wrong

- **Short retry window.** monday retries a failed webhook once a minute for 30 minutes. Longer outages lose events unless you reconcile.
- **Inconsistent labels.** "Done", "Complete" and "Shipped" across boards need a mapping table before anything is counted.
- **Column formats.** Column values are JSON whose shape depends on the column type; check the type before writing.
- **API exhaustion.** An MCP agent exploring boards can use the whole Standard daily allowance in a busy morning.

Teams that run delivery in other tools should compare our [Asana](/integrations/asana/) and [Jira](/integrations/jira/) guides.

## Questions people ask

### Do we have to buy monday AI credits?

If you joined the monday work platform on or after 6 May 2026, yes: AI credits are bought alongside seats, with monthly minimums of 1,000 on Basic, 2,000 on Standard and 3,000 on Pro. Earlier customers may be on older terms. The credit model covers the work platform only, not monday CRM, monday dev or monday service, and AI is not available on free accounts.

### Can Claude or ChatGPT read our monday.com boards?

Yes. monday runs a hosted Platform MCP server at https://mcp.monday.com/mcp with more than 60 tools. Each person authorises it with OAuth and sees only what they can see in monday. If someone cannot connect, an admin should check Admin, Permissions, AI Connectors. Every MCP tool call runs as an API request and counts toward your daily limit.

### Does the monday MCP server cost extra?

monday's help centre says MCP is available on all plans at no additional cost. The costs sit elsewhere: the AI assistant you connect it to has its own subscription, and heavy use can exhaust your daily API allowance, which is 1,000 calls on Standard and 10,000 on Pro. An agent that browses many boards can use hundreds of calls in one conversation.

### How do we stop AI changing project statuses?

Give custom integrations a token that can read boards and post updates but is not used to change columns, keep status changes with people, and have the summary job write only to a separate portfolio board. For MCP use, monday recommends reviewing AI-suggested changes before they apply; Enterprise admins can also limit which roles use AI features.


## Sources

- [The pricing model for monday AI portfolio](https://support.monday.com/hc/en-us/articles/35277848309394-The-pricing-model-for-monday-AI-portfolio)
- [monday.com pricing](https://monday.com/pricing)
- [API basics](https://developer.monday.com/api-reference/docs/basics)
- [Rate limits](https://developer.monday.com/api-reference/docs/rate-limits)
- [Platform MCP overview](https://developer.monday.com/api-reference/docs/mondaycom-mcp)
- [Webhooks](https://developer.monday.com/api-reference/reference/webhooks)
- [Pricing](https://platform.claude.com/docs/en/about-claude/pricing)
- [Privacy Act 2020](https://www.legislation.govt.nz/act/public/2020/31/en/latest/)

Published by Levy Street (https://levystreet.com), Wellington, New Zealand.