monday.com
Boards, groups, items and columns on monday.com via its GraphQL API.
About
monday.com ships in the w6w first-party pack. It declares 14 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
- App id
io.w6w.monday- Version
- 0.1.2
- Author
- w6w
- Licence
- MIT
- Categories
- Project Management · Productivity
Overview
monday.com organizes work as boards of items moving through groups and columns, and this app puts that structure under workflow control: create and read boards, groups and items, and change an item’s column values or move it between groups as work progresses.
Because monday’s entire API is GraphQL rather than a set of REST endpoints, every action here is really a purpose-built query or mutation against the one endpoint monday exposes, so a workflow just supplies the ids and values that matter and never has to construct GraphQL itself. Column values are the part most likely to trip up a hand-built integration, since monday expects them as a specific encoded structure rather than plain values — this app validates and encodes them, so a workflow can pass a straightforward value and trust it lands correctly.
Archiving a board and deleting a group are included for cleanup, and looking up a board’s own columns is there specifically to discover the ids a write needs before making one. This app stays at the level of boards and their contents — account and workspace administration aren’t part of it.
Build with monday.com
Three routes to the same 14 actions. The Workflow tab is generated from monday.com's own manifest and carries its real ids, so it is copy-pasteable; the Code and CLI examples are the same call for any action on any app, so every app-specific value in them is a blank you fill in.
List Columns
column-get-many List a board's columns with their ids and types — the keys column-value writes need.
Create Item
item-create Create an item on a board, optionally in a specific group and with column values.
List Items
item-get-many List items on a board, optionally within one group. Returns a page with a `cursor` for the next.
A workflow step names the app and the action, and the editor fills in the
connection when you pick one. This is the Step shape from the
workflow spec, carrying monday.com's real ids.
{
"manifestVersion": "2",
"name": "monday-example",
"steps": [
{
"id": "board-create",
"uses": {
"app": "io.w6w.monday",
"action": "board-create",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"name": "<name>",
"kind": "<kind>"
}
}
]
}Here are some of the things you can do
-
Create Board
performboard-create -
Get Board
readboard-get -
List Boards
searchboard-get-many -
List Columns
searchcolumn-get-many -
Create Group
performgroup-create
+9 more actions available
Every app-specific value here is a blank you have to fill in. An
app action is reached through the connection that authenticates it, so the
address is a connection id, not the app id — and connections belong to your account,
so a public page cannot know yours. Create one for monday.com, then fill in
the three blanks: conn_YOUR_CONNECTION_ID, the action key, and the
parameters that action declares. The call itself is real — the shape is transcribed
from the studio's own snippet builder, which prints the same kind of blanks — but
nothing in it is specific to monday.com. The Workflow tab is where this app's
real ids are.
npm install @w6w/sdkyarn add @w6w/sdkpnpm add @w6w/sdkdeno add npm:@w6w/sdkimport { W6wClient, isActionRun } from "@w6w/sdk";
// Reads W6W_BASE_URL and W6W_TOKEN from the environment when omitted.
const client = new W6wClient();
const envelope = await client.run({
urn: "conn_YOUR_CONNECTION_ID",
action: "item-create",
payload: {
boardId: "<value>",
itemName: "<value>",
// groupId: "<value>",
// columnValues: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value);npm install -g @w6w/cliw6w run conn_YOUR_CONNECTION_ID --action item-create --payload '{"boardId":"<value>","itemName":"<value>"}'Give an AI agent monday.com — without giving it monday.com's credentials. One MCP endpoint exposes every app, function and workflow the caller is entitled to, as tools it can discover and run. Access is granted per team while we onboard.
One tool call{
"name": "w6w_invoke",
"arguments": {
"ref": "app:io.w6w.monday#board-create",
"input": {
"name": "<name>",
"kind": "<kind>"
}
}
}
Every tool names its target with a single ref. The
app: form above doesn't name a connection at all — the
host resolves which of the caller's monday.com connections to sign
with, and refuses rather than guesses when the answer is ambiguous.
What the agent gets
Credentials it can't read
The token is attached host-side, at the moment of the call. It is never a tool argument, never in the model's context, and never in a transcript — so a prompt injection has nothing to exfiltrate.
A tool surface scoped to the caller
Tools are derived per end user from what that person has actually connected and is entitled to — not one shared bot identity carrying the union of everyone's access.
A durable workflow in one call
Multi-step work runs on the workflow engine and returns a run handle the agent can poll — retries, branching and state survive the conversation that started them.
Health-aware discovery
monday.com's declared health checks are on the surface too, so an agent can tell "the vendor is down" from "your credential expired" before it burns a retry on either.
The MCP surface is part of the hosted platform. monday.com itself is MIT, and the runtime that executes it is source-available (FSL).
Health checks
monday.com declares its own checks, so its health is a property of the app rather than something the host guesses at.
monday.com platform status
Atlassian Statuspage rollup for status.monday.com, with per-component detail. Unauthenticated and unsigned.
API complexity headroom
Query-complexity budget remaining, read off monday's top-level `complexity` object (`after` / `reset_in_x_seconds`).