Manage MeisterTask projects, sections, tasks, checklists, labels and comments via the MeisterTask REST API.
MeisterTask ships in the w6w first-party pack. It declares 38 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
io.w6w.meistertaskMeisterTask is a Kanban-style project and task manager from the Meister suite (alongside MindMeister). This app covers the everyday project-management path: creating and organising projects, moving work between the sections that make up a project board, and creating, updating and reading the tasks and subtasks that live on it.
A task’s supporting detail is covered too — checklists and checklist items for breaking work down further, labels for categorising tasks project-wide, and comments for discussion on a task — plus read access to the people who make up a team, so a workflow can look up who to assign work to.
Authentication follows the vendor’s own two paths: a personal access token for a single account’s own automations, or a full OAuth 2.0 flow (delegated through MindMeister’s authorization server, which MeisterTask shares) for a public integration serving many end users.
Three routes to the same 38 actions. The Workflow tab is generated from MeisterTask'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.
checklist-item-update Rename a checklist item, re-sequence it, or change its status (e.g. mark it done).
label-create Create a label in a project. The name must be unique (case-insensitive) within the project.
person-list List every person visible to this account — useful for looking up an assignee's person ID before creating or updating a task.
project-duplicate Create a copy of a project, optionally including its tasks, checklists, labels, attachments and project rights.
project-members-list List a project's members: individual project rights plus, on the Business plan, group and team memberships.
task-label-add Attach an existing label to a task. The label must already exist in the task's project — see label-create.
task-label-list List the labels attached to a task, as the join records — each carries the task-label ID that task-label-remove needs.
task-label-remove Detach a label from a task, given the task-label join ID (from task-label-list or task-label-add).
task-update Update a task's name, description, assignee, due date, status or section — moving it between sections is how a task changes Kanban column.
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 MeisterTask's real ids.
{
"manifestVersion": "2",
"name": "meistertask-example",
"steps": [
{
"id": "checklist-create",
"uses": {
"app": "io.w6w.meistertask",
"action": "checklist-create",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"taskId": "<taskId>",
"name": "<name>"
}
}
]
}checklist-create checklist-item-create checklist-item-list checklist-item-update checklist-list +33 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 MeisterTask, 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 MeisterTask. 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: "checklist-create",
payload: {
taskId: "<value>",
name: "<value>",
// sequence: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action checklist-create --payload '{"taskId":"<value>","name":"<value>"}' Give an AI agent MeisterTask — without giving it MeisterTask'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.meistertask#checklist-create",
"input": {
"taskId": "<taskId>",
"name": "<name>"
}
}
}
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 MeisterTask connections to sign
with, and refuses rather than guesses when the answer is ambiguous.
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.
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.
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.
MeisterTask'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. MeisterTask itself is MIT, and the runtime that executes it is source-available (FSL).
MeisterTask declares its own checks, so its health is a property of the app rather than something the host guesses at.
Page-level status plus the API component, read from status.meistertask.com (a Sorry-hosted status page, not Statuspage/Instatus).