Confluence MCP. Search, read, and write to your company wiki from chat.

Q: Can I use getpage if I only know the title?

No. getpage requires a specific page ID. If you only know the title, you must first run listpages or searchconfluence to find the correct ID.

Q: What is the difference between listpages and listspaces?

Use listspaces first to get a list of all available top-level departments or sections. Then, use listpages on a specific space key to enumerate all the pages within that section.

Q: How do I list all available spaces using the listspaces tool?

You call listspaces with no parameters. It returns a list of all available spaces within your Confluence instance. This list is necessary to know the correct space key for other operations.

Q: If I use getpage, how do I view the page's revision history and metadata?

getpage returns detailed information about a specific page, including its content body, space, metadata, and version history. You don't need separate calls to access this data.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Just plug in your AI agents and start using Vinkius.

Confluence MCP Server lets your AI agent search, read, and write to your company wiki. You can query technical documentation, find HR policies, and publish formatted pages directly from your chat window.

It connects your AI client to your Atlassian Confluence workspace.

What your AI agents can do

Add label

Labels help organize and filter wiki content.

Add a label to a Confluence page

Add page comment

Adds a new comment to a specific Confluence page.

Create page

Creates a brand new page in a specified Confluence space with provided title and content.

+ 9 more capabilities included

Search the entire wiki

You ask the agent for content on a topic, and it executes search_confluence to find matching pages, blog posts, and comments across the entire space.

Retrieve and analyze page content

You request a specific page by ID, and the agent uses get_page to pull the body, metadata, and version history for review.

Draft and publish new documents

You instruct the agent to write a new document (like a PRD), and it uses create_page to publish the formatted content to your designated space.

Manage space structure

You ask the agent for a list of available spaces or pages, and it runs list_spaces or list_pages to map out your organizational structure.

Pinpoint comments and discussions

You need to know who said what on a specific page, and the agent uses list_page_comments to pull all inline and footer comments.

Ask AI about this MCP

Ask ChatGPT

Ask Claude

Ask Perplexity

Supported MCP Clients

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

+ other MCP clients

Free for Subscribers

Waiting for input…

AI Agent

add019e9aa4

add label

Labels help organize and filter wiki content. Add a label to a Confluence page

add019d7579

add page comment

Adds a new comment to a specific Confluence page.

create019d7579

create page

Creates a brand new page in a specified Confluence space with provided title and content.

delete019e9aa4

delete page

This action is irreversible. Delete a Confluence page permanently

get019d7579

get page

Retrieves the full content, metadata, and version history for a single Confluence page.

get019e9aa4

get page history

Retrieve the version history of a Confluence page

get019d7579

get space details

Fetches the metadata, description, and permissions overview for a specific Confluence space.

list019e9aa4

list labels

List all labels on a Confluence page

list019d7579

list page comments

Retrieves all comments (inline and footer) associated with a given Confluence page.

list019d7579

list pages

Retrieves a paginated list of all pages within a specified Confluence space.

list019d7579

list spaces

Gets a list of every space available in your Confluence instance.

search019d7579

search confluence

Searches the entire wiki using Confluence Query Language (CQL) for matching pages, blog posts, and comments.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with Confluence, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 4,700+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

What you can do with this MCP connector

Your AI agent connects straight to your Confluence workspace. You can search, read, and write to your company wiki right from your chat. It's built for anyone who needs to manage knowledge or pull info from Confluence without switching tabs.

Searching the Whole Damn Wiki

You tell your agent what you're looking for, and it runs search_confluence to find matching pages, blog posts, and comments across your entire wiki. You can query everything—software architecture decisions, HR policies, meeting notes—and get a list of results.

Handling Page Content

Need to check out a specific page? Your agent uses get_page to pull the full content, metadata, and version history for that single page. It's got all the deep details. If you want to know what's going on with your spaces, it'll run get_space_details to fetch the metadata, description, and permissions overview for a specific space.

You can also map out your whole setup by asking it to list all available spaces using list_spaces, or pull a list of all pages within a space using list_pages.

Drafting and Publishing New Stuff

Want to write a new document, like a PRD or meeting minutes? Just tell your agent to write it, and it uses create_page to publish the formatted content directly to your designated Confluence space. If you need to mark up something already published, it'll run add_page_comment to add a new comment to a specific page, or it'll pull every comment—both inline and footer—associated with a page using list_page_comments.

Putting It All Together

Your agent can search the whole wiki with search_confluence. When you find a page, you can pull its full content and metadata with get_page. You can also manage the structure by listing all spaces (list_spaces) or listing pages in a space (list_pages). You'll never be stuck in the knowledge jungle again.

How Confluence MCP Works

1 Install the Confluence MCP server integration and authorize it with your Atlassian API Token.
2 Your AI client sends a prompt (e.g., 'Summarize the Q3 migration plan').
3 The agent selects the appropriate tool (e.g., search_confluence), executes it, and presents the summarized results back to you in the chat.

The bottom line is that you use your AI client to talk to your company's wiki, and the agent handles the API calls to pull or push data.

Who Is Confluence MCP For?

The software engineer who needs to reference an old architecture decision without leaving their IDE. The product manager who needs to turn meeting notes into a formal PRD instantly. Or the HR specialist who needs to quote a specific policy section in a live conversation.

Software Engineer

Uses search_confluence to find technical guidelines and architectures, then uses get_page to pull specific requirements for review.

Product Manager

Uses create_page to draft and publish PRDs or sprint notes, and list_pages to check the existing structure in a space.

Technical Writer

Uses search_confluence and get_page to pull existing technical documentation, then uses add_page_comment to suggest updates or questions.

What Changes When You Connect

See technical guidelines instantly. Instead of opening 10 browser tabs, use search_confluence to find architecture decisions or policies across your entire wiki.
Never lose meeting notes again. Use create_page to draft a PRD or meeting minutes, then publish it directly to the correct 'Product' space without copy-pasting.
Get the full context of any document. Running get_page pulls the complete text, metadata, and version history of a page, so you don't rely on summaries.
Map out your entire knowledge base. Tools like list_spaces and list_pages let you list all available content, so you know where to look next.
Track team feedback. If you need to know who questioned a policy, use list_page_comments to pull all comments and authors for a specific page.

Real-World Use Cases

Finding a specific policy document

An HR agent needs to reference the 'PTO policy'. Instead of manually navigating the HR space and filtering through folders, the agent executes search_confluence with the query. It returns the exact document link and a summary, solving the manual search bottleneck.

Formalizing meeting outcomes

The PM finishes a sprint planning meeting. Instead of copying bullet points into a Word document and manually uploading it, the agent drafts the summary and executes create_page into the 'Sprint Notes' space. The documentation is live immediately.

Reviewing an old technical spec

A junior engineer needs to know the original design choice for a microservice. The agent uses get_page on the known page ID. It returns the full, historical content, including version notes, allowing the engineer to understand the 'why' behind the code.

Auditing a space's contents

A manager wants to see everything housed in the 'Department X' space. The agent runs list_pages to get an enumeration of all page titles and IDs, giving the manager a complete inventory of the space's content.

The Tradeoffs

Searching only by keyword

Typing 'migration' into the search bar and getting 50 results. You have to click 10 links to find the right policy document.

→ Use search_confluence with a targeted query like text ~ "migration" AND type = "page". This filters the results immediately, giving you only relevant page content, not blog posts or comments.

Copying content manually

Copying a section of text from a wiki page into a PRD, and losing the original formatting or markdown structure.

→ Use the agent to execute get_page. It retrieves the full content and markdown structure, allowing you to pass clean, formatted text directly into your new document via create_page.

Trying to guess the page ID

You know the page exists, but you don't know its unique ID, so you just search and hope it pops up first.

→ First, use list_pages to check the space structure and find the page title or ID. Once you have the ID, use get_page to guarantee you pull the correct, complete version of the document.

When It Fits, When It Doesn't

Use this if you need to treat your Confluence wiki like a database—meaning you need to programmatically search, read, or write structured content. You need to automate the process of moving knowledge from a static wiki into a structured workflow.

Don't use this if your goal is simply to read a single, known article on a personal laptop. For that, a standard browser search is faster. If you only need to know which spaces exist, use list_spaces first to scope the problem, then drill down with list_pages or search_confluence to find the content.

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Confluence. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

How we secure it →

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This server provides 12 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.

Available Capabilities

add_label add_page_comment create_page delete_page get_page get_page_history get_space_details list_labels list_page_comments list_pages list_spaces search_confluence

Finding the right policy document shouldn't require three different browser tabs.

Today, finding a specific policy means clicking into the Confluence site, navigating to the correct department space (HR, Engineering, etc.), then using the internal search bar, and finally sifting through pages that might be blog posts or meeting notes. It's a lot of clicks and context switching.

With this MCP server, you just ask your agent: 'What is the latest PTO policy?' The agent executes `search_confluence` against all spaces, returning the exact, relevant document link and a summary in your chat. The whole process takes seconds.

Confluence MCP Server: Publish content with `create_page`

Manual documentation requires copying meeting notes into a draft, ensuring the right space is selected, and then manually hitting the 'Publish' button. This process is prone to human error and slows down the documentation cycle.

Now, you draft the PRD with your AI client, and when it's ready, you tell the agent to run `create_page`. The document is formatted and published instantly to the designated space. It's a direct workflow.

Common Questions About Confluence MCP

How do I use the `search_confluence` tool? +

You tell the agent what you're looking for. The agent handles the Confluence Query Language (CQL) syntax. You just provide the topic, like 'Q3 Migration Plan', and the agent executes the search.

Can I use `get_page` if I only know the title? +

No. get_page requires a specific page ID. If you only know the title, you must first run list_pages or search_confluence to find the correct ID.

What is the difference between `list_pages` and `list_spaces`? +

Use list_spaces first to get a list of all available top-level departments or sections. Then, use list_pages on a specific space key to enumerate all the pages within that section.

How do I add a comment using `add_page_comment`? +

You provide the target page ID, the comment body (in HTML format), and the comment type (inline or footer). The agent handles the payload structure.

Does `search_confluence` search everything? +

Yes. The tool searches matching pages, blog posts, and comments across your entire Confluence instance using CQL.

What parameters does `create_page` require, and what format should the body content be in? +

It requires the space key, a title, and the body content. The body content must be in Confluence storage format (HTML). This ensures the AI client formats the page correctly for publishing.

How do I list all available spaces using the `list_spaces` tool? +

You call list_spaces with no parameters. It returns a list of all available spaces within your Confluence instance. This list is necessary to know the correct space key for other operations.

If I use `get_page`, how do I view the page's revision history and metadata? +

get_page returns detailed information about a specific page, including its content body, space, metadata, and version history. You don't need separate calls to access this data.

How do I generate an Atlassian API Token? +

Log into your Atlassian account at id.atlassian.com, navigate to the Security tab, and click on API tokens. Select 'Create and manage API tokens' to generate a new key for this integration.

Can the AI edit all spaces within my Confluence account? +

The AI integration adheres strictly to the permissions of the user generating the API token. It can only read and modify the spaces that your specific Atlassian user account has authorization to access.

Does a published Confluence page support Markdown? +

Yes, Confluence correctly processes standard formatting such as headings, lists, code blocks, and rich text when the AI agent generates and uploads content.

View all recipes →