# monday for AI agents. Make the right board item easier to review.

> Read accessible board items and related records in monday. Prepare a source-grounded board progress briefing within the selected account.

- Page: https://www.agent200.com/connectors/monday/
- Category: Developer tools
- Authentication: Managed OAuth
- Identifier in code: `monday`
- Create an API key: https://agent200.com/platform/apikeys/
- Updated: 2026-11-18

## Instructions for AI agents

Connector: monday, through Agent200. In code: "monday".
What it does: Read accessible board items and related records in monday. Prepare a source-grounded board progress briefing within the selected account.
Page: https://www.agent200.com/connectors/monday/

1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs.
2. Sign-in is managed OAuth. Each end user approves access once, on monday's own page, through the authorization link Agent200 returns. Never ask a user for a monday password or token in chat.
3. Give every request a stable id for the end user. Agent200 uses only that user's own connection.
4. Read tools: monday_list_boards, monday_get_board, monday_list_items, monday_get_item, monday_search_items. Name "monday" in the tools of a request; the model decides which tool to call.
5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it.
6. Before a write, confirm with the user, unless they asked for that exact change.
7. For setup with a specific framework, follow its guide:
   https://www.agent200.com/connectors/monday/framework/claude/
   https://www.agent200.com/connectors/monday/framework/chatgpt/
   https://www.agent200.com/connectors/monday/framework/claude-code/
   https://www.agent200.com/connectors/monday/framework/muse/
   https://www.agent200.com/connectors/monday/framework/grok-bot/
   https://www.agent200.com/connectors/monday/framework/openai-dots/
   https://www.agent200.com/connectors/monday/framework/claude-duet/
   https://www.agent200.com/connectors/monday/framework/hermes-agent/
   https://www.agent200.com/connectors/monday/framework/openclaw/

The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

## About

With the monday connector, your agent reads boards and items in each user's own monday account. It can list boards, read a board, list the items on it, and search items, using only the tools your project allows.

monday is a work management platform for planning and tracking team work on boards.

## monday tools

- **List boards** (`monday_list_boards`, read): Find boards visible to the connected user.
- **Read a board** (`monday_get_board`, read): Retrieve one identified board and its fields.
- **List items** (`monday_list_items`, read): Find items on an accessible board.
- **Read an item** (`monday_get_item`, read): Retrieve one identified item and column values.
- **Search items** (`monday_search_items`, read): Search accessible items with a scoped query.

## Limits you can set

**Turn single tools on or off.** Let the agent read boards and items, and switch off `monday_search_items` if it should only list items on a board.

**Restrict what the agent reaches.** Choose the endpoints and scopes a project may use, for example boards but not items. A call outside them is refused.

## Get started

### Step 1: Set up the SDK

Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.

File `agent.js`:

```js
// One Agent200 API key covers every connector enabled for the project.
const agent200 = new Agent200({
  apiKey: process.env.AGENT200_API_KEY,
});
```

(Conceptual example of the Agent200 SDK.)

### Step 2: Let your user connect monday

Each end user authorizes their own monday account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.

File `connect.js`:

```js
// Each end user authorizes their own monday account, once.
const connection = await agent200
  .user("user_123")
  .connect("monday");

if (connection.authorizationUrl) {
  // Show this link to your user; Agent200 handles the rest.
  console.log(connection.authorizationUrl);
}
```

(Conceptual example of the Agent200 SDK.)

### Step 3: Run with the monday tools

Name the user, the model and the tools. The model decides which monday tools to call, and Agent200 executes them with that user's connection.

File `run.js`:

```js
const result = await agent200
  .user("user_123")
  .run({
    model: "openai/gpt-5.6-sol",
    input: "List the boards in my monday account",
    tools: ["monday"],
  });

console.log(result.output);
```

(Conceptual example of the Agent200 SDK.)

## Sign-in and permissions

**Connect the intended account.** Use the documented monday authorization route. Confirm the organization, team or workspace before reading records.

**Match access to the request.** Authorize the correct monday account with boards:read. GraphQL results follow board and item permissions; viewers and disabled users may lack API access.

**Preserve the application user.** Keep the same stable application user identity for connection and later requests. Store the Agent200 key outside prompts and code.

## Example requests

- "List the boards in my monday account"
- "Which items on the Sprint board are stuck"
- "Find the item for the website launch"

## Guides: monday with your AI framework

- [monday + Claude](https://www.agent200.com/connectors/monday/framework/claude.md): Read board items with Claude and Agent200. Prepare a board progress briefing using the connected user’s own monday account.
- [monday + ChatGPT](https://www.agent200.com/connectors/monday/framework/chatgpt.md): Use ChatGPT to build a separate read-only monday assistant with Agent200. Ground the board progress briefing in returned source data.
- [monday + Claude Code](https://www.agent200.com/connectors/monday/framework/claude-code.md): Use Claude Code to build a separate read-only monday assistant with Agent200. Ground the board progress briefing in returned source data.
- [monday + Muse](https://www.agent200.com/connectors/monday/framework/muse.md): Read board items with Muse and Agent200. Prepare a board progress briefing using the connected user’s own monday account.
- [monday + Grok Bot](https://www.agent200.com/connectors/monday/framework/grok-bot.md): Read board items with Grok Bot and Agent200. Prepare a board progress briefing using the connected user’s own monday account.
- [monday + OpenAI Dots](https://www.agent200.com/connectors/monday/framework/openai-dots.md): Use OpenAI Dots to build a separate read-only monday assistant with Agent200. Ground the board progress briefing in returned source data.
- [monday + Claude Duet](https://www.agent200.com/connectors/monday/framework/claude-duet.md): Read board items with Claude Duet and Agent200. Prepare a board progress briefing using the connected user’s own monday account.
- [monday + Hermes Agent](https://www.agent200.com/connectors/monday/framework/hermes-agent.md): Read board items with Hermes Agent and Agent200. Prepare a board progress briefing using the connected user’s own monday account.
- [monday + OpenClaw](https://www.agent200.com/connectors/monday/framework/openclaw.md): Read board items with OpenClaw and Agent200. Prepare a board progress briefing using the connected user’s own monday account.

## FAQ

### What access does monday need?

Authorize the correct monday account with boards:read. GraphQL results follow board and item permissions; viewers and disabled users may lack API access. [Provider documentation](https://developer.monday.com/api-reference/docs/basics).

### Does a list include every record?

Column meanings are board-specific. Resolve status labels and pagination from the selected board; search is result-limited.

### Can this workflow make changes?

The listed monday operations are read-only. A proposed change in the agent answer does not edit the source.

### How should I verify the answer?

Identify the selected board item and compare the answer with board, item, status and date fields. Disclose missing or inaccessible fields.

### Are these exact runtime tool schemas?

The listed identifiers describe catalogue capabilities. Discover the actual runtime tool names and input schemas before executing a request.

## Related connectors

- [GitHub](https://www.agent200.com/connectors/github.md): Read repositories and work with issues and pull requests as the connected user.
- [GitLab](https://www.agent200.com/connectors/gitlab.md): Review merge requests, file issues, read code and check pipelines in your users' GitLab projects.
- [Bitbucket](https://www.agent200.com/connectors/bitbucket.md): List and open pull requests, comment, read code and check pipelines in your users' Bitbucket workspaces.
- [Jira](https://www.agent200.com/connectors/jira.md): Search, create and transition Jira issues for the connected user.

---

Agent200: https://www.agent200.com/ · API keys: https://agent200.com/platform/apikeys/ · Docs: https://docs.igpt.ai/
