Confluence MCP Server
Connect to the Confluence MCP server to create and update pages, browse spaces, manage blog posts, and read content across your team wiki using AI agents on Gumloop, Claude, or Cursor.
Try Confluence now
Type what you want done. Sign in and run it live with an AI agent.
|
Confluence
Installation
Get StartedCreate a Gumloop Account
To use this MCP, you need a Gumloop account. If you don't have one yet, you can create one for free.
Copy Your Server URL
Copy your MCP server URL and add it to your client. You'll be prompted to authorize on first use.
Tools (18)
List Sites
List all Atlassian/Confluence sites the authenticated credential can access, to discover the cloud_id or site_name required by other tools when multiple sites are available.
List Pages
Returns all pages from Confluence. Filter pages by id, space-id, status, title, or sort.
Get Page
Returns a specific page by ID with comprehensive details including body content, labels, properties, operations, likes, and versions.
Create Page
Creates a new page in a Confluence space. Pages are created as published by default unless specified as draft. Published pages require a title.
Update Page
Update a page by id. When updating 'current' version, content is merged into draft. Changing status from 'current' to 'draft' deletes existing draft. Can restore 'trashed' or 'deleted' pages to 'current' status.
Get Database
Returns a specific database by ID with optional includes for collaborators, direct children, operations, and properties.
List Tasks
Returns all tasks. Filter tasks by status, task-id, space-id, page-id, blogpost-id, created-by, assigned-to, or completed-by.
Get Task
Returns a specific task by ID with optional body format specification.
Update Task
Update a task by id. Currently only supports updating task status (complete/incomplete).
List Blogposts
Returns all blog posts. Filter by id, space-id, status, title, or sort.
Get Blogpost
Returns a specific blog post by ID with optional includes for labels, properties, operations, likes, versions, and collaborators.
Create Blogpost
Creates a new blog post in a space. By default creates as non-draft unless status is specified as draft.
What is Confluence MCP?
The Confluence MCP server gives AI agents access to your Confluence Cloud wiki. That means agents can find pages by space, title, or status, read full page content with its labels and version history, create and update pages and blog posts, browse spaces, track tasks, and handle attachments. It works across the core Confluence objects your team relies on: spaces, pages, blog posts, databases, tasks, and attachments.
If your team spends time copying meeting notes into the wiki, hunting for the right page across dozens of spaces, updating docs by hand, or chasing down where a decision was written, an AI agent can take over much of that busywork. Describe what you need, and your AI agent will handle the documentation work for you.
MCP stands for Model Context Protocol. It’s an open standard that gives AI agents a way to connect to external tools and services. Instead of registering an Atlassian OAuth app, managing client IDs and secrets, and writing code against the Confluence Cloud REST API, you connect your Atlassian account once. After that, you can manage your wiki just by chatting with your AI agent.
Related MCP servers
Notion MCP Server
Server for interacting with Notion
Google Docs MCP Server
Create and manage Google Docs documents
JIRA MCP Server
Interact with JIRA for project management, issue tracking, and user information access.
Linear MCP Server
Interact with Linear issue tracking and project management
Slack MCP Server
Interact with Slack channels and messages
Google Drive MCP Server
Search and access files in Google Drive
What you can do with Confluence MCP on Gumloop
Find and read pages
List pages filtered by space, title, or status, then pull full page content along with its labels, properties, and version history. Your AI agent can locate the right doc and summarize it for you without clicking through spaces.
Create and update pages
Create new pages as drafts or published, update the content and title of existing pages, and restore trashed or deleted pages back to current. Your agent can stand up a new doc or revise an existing one on request.
Manage blog posts
Create, read, list, and update Confluence blog posts, including drafts. An agent can publish a team update or pull the latest announcements into a summary.
Browse spaces
List spaces and filter by keys, type, or status to find where content lives. This gives an agent the map it needs before reading or writing pages.
Track tasks
List and read tasks across pages and blog posts, filter by assignee, creator, or status, and mark tasks complete or incomplete. Useful for rolling up open action items or closing out finished work.
Handle attachments
List attachments on a page or blog post, download attachment files into Gumloop storage so an agent can read or analyze them, upload new files from Gumloop storage to a page, and delete attachments you no longer need.
Read Confluence databases
Pull a database by ID along with its properties, direct children, and collaborators, so an agent can reference structured content that lives in a space.
Pull page metadata and history
Read labels, likes, operations, and version history on pages, plus collaborators on blog posts, to see how content has changed and who touched it.
How to connect the Gumloop Confluence MCP Server
- 1
Create a free Gumloop account
Sign up at gumloop.com. No credit card required.
- 2
Add the Confluence MCP server
Copy your MCP server URL from Gumloop and add it to your preferred client (Claude, Cursor, or Gumloop workflows). You'll authorize on first use.
- 3
Start using Confluence in your AI workflows
That's it. Your AI agent can now find pages, create and update content, manage blog posts, track tasks, and handle attachments across your Confluence Cloud wiki. Use it inside a Gumloop automation, in Claude Desktop, or in Cursor.
Confluence MCP use cases
Meeting notes to wiki for operations teams
After a meeting, a Gumloop agent can take the raw notes from a transcript or a Slack thread, format them into a clean summary with action items, create a new Confluence page in the right space, and post the link back to the team in Slack. The wiki stays current without anyone writing it up by hand.
Knowledge base upkeep for documentation teams
An agent can list pages in a space, read each one, flag docs that look stale or contradictory, and draft updated versions for a writer to approve. When a product detail changes, the agent updates every affected page instead of someone searching for them one by one.
Release notes and changelog drafting for engineering teams
Pull merged work from GitHub or Linear, have an AI agent group it into themes, then create or update a release notes page and a Confluence blog post announcing the launch. Engineers ship the changelog without leaving their normal tools.
Project status pages for product managers
A PM can have an agent read open tasks across project pages, pull status from Jira, and update a single project status page with what shipped, what slipped, and what’s next. The status page refreshes on a schedule so the team always sees the current picture.
Support knowledge sync for support teams
When a new fix or policy lands, an agent can draft a help article as a Confluence page, attach a relevant screenshot from Gumloop storage, and notify the support channel. Recurring tickets turn into documented answers the whole team can reuse.
Why use Gumloop for Confluence MCP
Connect your Atlassian account, no OAuth app to register
Most Confluence MCP servers you’ll find on GitHub make you register an Atlassian OAuth app, manage client IDs and secrets, and handle token refresh in your own code. With Gumloop you authorize your Atlassian account once and stay connected. Gumloop handles authentication and refreshes your access in the background, with no secrets to store and no code to write.
Works with multiple MCP clients
Use the Confluence MCP server endpoint in Claude Desktop, Cursor, or directly inside Gumloop agents. Same server URL, works with any MCP client.
Chain Confluence with 100+ other integrations
Combine Confluence with Slack, Jira, GitHub, Google Docs, and other MCP tools in a single AI agent. An agent can pull updates from one tool, process them with an LLM, and write a clean page or blog post back to your wiki.
Enterprise-grade and scalable
Built for teams, with role-based permissions and dedicated support for Pro users. For details on Gumloop’s security practices, see trust.gumloop.com.
Pricing includes a free plan
You can test the Confluence MCP integration on Gumloop’s free tier before committing. Paid plans start at $37/month.
Frequently asked questions
Ship Confluence agents in minutes
Connect any AI agent to 100+ MCP servers, zero setup.