First-party app
Confluence Confluence

Confluence

Read and write Confluence Cloud pages, spaces, blog posts, comments and tasks.

stable Documents & FilesProductivity

About

Confluence ships in the w6w first-party pack. It declares 22 actions, 3 health checks, and the host runs its code in a sandbox that never sees the credential.

App id
io.w6w.confluence
Version
0.1.1
Author
w6w
Licence
MIT
Categories
Documents & Files · Productivity

Overview

Confluence Cloud is Atlassian’s team wiki, and this app reads and writes its pages, spaces, blog posts, comments, and inline tasks — everything a workflow needs to publish documentation, keep a knowledge base current, or pull content into another system. Pages can be created, updated, listed by space or title, and searched with Confluence’s own query language; spaces can be created and browsed, including as a tree of child pages; and blog posts can be published into a space the same way.

Comments and tasks round it out: the discussion thread at the bottom of a page can be read and posted to, and a workflow can list the inline action items assigned across a space, filterable by status or assignee. Content search covers the single most useful thing a workflow does with a wiki — finding what mentions something and has changed recently — even where Confluence’s current API doesn’t otherwise offer a search endpoint of its own.

Build with Confluence

Three routes to the same 22 actions. The Workflow tab is generated from Confluence'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.

Get an attachment

attachment-get

Retrieve one attachment's metadata, including its download link.

Create a blog post

blogpost-create

Publish a blog post in a space.

Get a blog post

blogpost-get

Retrieve one blog post by ID.

List blog posts

blogpost-list

List blog posts, optionally filtered by space, title or status.

Add a comment

comment-create

Add a footer comment to a page or blog post, or reply to another comment.

Delete a comment

comment-delete

Remove a footer comment.

Search content (CQL)

content-search

Search pages, blog posts and attachments with a CQL query.

List a page's attachments

page-attachment-list

List the files attached to one page.

List a page's children

page-child-list

List the pages directly beneath one page.

List a page's comments

page-comment-list

List the footer comments on one page.

Create a page

page-create

Create a page in a space, optionally under a parent page.

Delete a page

page-delete

Move a page to the trash, or purge one already in the trash.

Get a page

page-get

Retrieve one page, optionally including its body, labels or version history.

List a page's labels

page-label-list

List the labels on one page.

List pages

page-list

List pages, optionally filtered by space, title or status.

Update a page

page-update

Change a page's title, body, status or parent.

Create a space

space-create

Create a new space, optionally private.

Get a space

space-get

Retrieve one space by its numeric ID.

List spaces

space-list

List spaces, optionally filtered by key, type or status.

List a space's pages

space-page-list

List the pages in one space, optionally only the root-level ones.

List tasks

task-list

List the inline tasks in pages and blog posts, filtered by status or assignee.

Get the current user

user-current

Retrieve the account this connection authenticates as.

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 Confluence's real ids.

{
  "manifestVersion": "2",
  "name": "confluence-example",
  "steps": [
    {
      "id": "attachment-get",
      "uses": {
        "app": "io.w6w.confluence",
        "action": "attachment-get",
        "connection": "conn_YOUR_CONNECTION_ID"
      },
      "with": {
        "attachmentId": "<attachmentId>"
      }
    }
  ]
}

Here are some of the things you can do

  • Get an attachment

    read
    attachment-get
  • Create a blog post

    perform
    blogpost-create
  • Get a blog post

    read
    blogpost-get
  • List blog posts

    read
    blogpost-list
  • Add a comment

    perform
    comment-create

+17 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 Confluence, 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 Confluence. The Workflow tab is where this app's real ids are.

Install
npm install @w6w/sdk
yarn add @w6w/sdk
pnpm add @w6w/sdk
deno add npm:@w6w/sdk
Code
import { 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: "attachment-get",
  payload: {
    attachmentId: "<value>",
    // version: "<value>",
    // includeLabels: "<value>",
  },
});

if (isActionRun(envelope)) console.log(envelope.value);
Install the CLI
npm install -g @w6w/cli
CLI
w6w run conn_YOUR_CONNECTION_ID --action attachment-get --payload '{"attachmentId":"<value>"}'

Give an AI agent Confluence — without giving it Confluence'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.confluence#attachment-get",
    "input": {
      "attachmentId": "<attachmentId>"
    }
  }
}

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 Confluence 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

Confluence'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. Confluence itself is MIT, and the runtime that executes it is source-available (FSL).

Request MCP access

Health checks

Confluence declares its own checks, so its health is a property of the app rather than something the host guesses at.

service

Confluence platform status

Atlassian Statuspage rollup for confluence.status.atlassian.com, with per-component detail. Unauthenticated and unsigned.

dependency

Confluence site reachable

Unauthenticated `GET /status` against this connection's Atlassian site — proves the site exists and is serving.

quota

API quota headroom