Integration

Confluence Data Center integration

Confluence Data Center is Atlassian's self-hosted wiki (REST API v1 on your own server; the Atlassian Cloud product is a separate integration). Read, create, update, move, trash and delete pages and blog posts, find content by space and title or with a CQL query, read comments and attachments, convert a body between storage and view formats, manage labels and content properties, list, create, update and delete spaces and read their content and labels, look up users and groups, and follow long-running tasks such as a space deletion. Not exposed: administration (global and space permissions, backup and restore, indexing, cluster, audit, webhooks), attachment uploads, user and group changes and password routes. Authentication is a personal access token (avatar > Settings > Personal access tokens, Confluence 7.9 and later) sent as a Bearer token, or a username and password (Basic); the connection also asks for the server's base URL, including any context path such as /confluence.

Connect Confluence Data Center How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Confluence Data Center.Built from the 37 Confluence Data Center tools below, on the connection you add once.

What you can do with Confluence Data Center

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Content, 6 operations

create_contentCreate contentPOSTCreates a page or blog post in a space, optionally as the child of a page (ancestors), with its body in storage format, and returns it.
delete_contentDelete contentDELETETrashes a current page or blog post; called again with status=trashed on trashed content, it purges it for good. Content that cannot be trashed is deleted at once.
get_contentGet contentGETReturns one page, blog post, comment or attachment. Use expand=body.storage,version to get its content and version number (needed by update_content).
list_contentList contentGETLists pages or blog posts, filtered by space key, title, posting day (blog posts) or status, 25 per page by default. Use expand=body.storage to get the page content.
list_space_content_by_typeList space content by typeGETLists the pages or the blog posts of a space, all of them or only the root ones (depth=root).
update_contentUpdate contentPUTUpdates a page or blog post: title, body, parent (ancestors) or position, or restores it from the trash. A body sent replaces the whole current body. version.number must be the current number plus one; send type and title too.

Property, 5 operations

create_content_propertyCreate content propertyPOSTStores a new content property (a key with a JSON value) on a page or blog post and returns it.
delete_content_propertyDelete content propertyDELETEDeletes a content property from a page or blog post.
get_content_propertyGet content propertyGETReturns one content property of a page or blog post with its JSON value and version.
list_content_propertiesList content propertiesGETLists the content properties of a page or blog post (key, JSON value, version), used by apps to store data on a page.
update_content_propertyUpdate content propertyPUTReplaces the value of a content property: send its id and version.number as the current number plus one (version 1 creates a property that does not exist yet).

Space, 5 operations

create_spaceCreate spacePOSTCreates a space with a key and a name (and a description) and returns it.
delete_spaceDelete spaceDELETEDeletes a space and all its content in a background task, and returns the task's id: follow it with get_long_task until it completes.
get_spaceGet spaceGETReturns one space (key, name, type, status); use expand=description,homepage for its description and home page.
list_spacesList spacesGETLists spaces, optionally only some keys, ids, labels, favourites, a type (global or personal) or a status (current or archived), 25 per page by default.
update_spaceUpdate spacePUTUpdates a space's name or description. The vendor requires key and name in every update; send the description too to keep it.

Label, 4 operations

add_content_labelsAdd content labelsPOSTAdds labels to a page or blog post and returns its labels.
list_content_labelsList content labelsGETLists the labels of a page or blog post (prefix and name), optionally only some prefixes (global, my, team).
list_space_labelsList space labelsGETLists every label used by the pages, blog posts and other content of a space.
remove_content_labelRemove content labelDELETERemoves one label from a page or blog post. A label name containing / cannot be removed this way.

Attachment, 2 operations

delete_attachmentDelete attachmentDELETEDeletes an attachment from a page or blog post.
list_attachmentsList attachmentsGETLists the attachments of a page or blog post (file name, media type, version), optionally only one file name or media type.

Longtask, 2 operations

get_long_taskGet long taskGETReturns a long-running task's progress: percentage complete, elapsed time, whether it succeeded, and its messages.
list_long_tasksList long tasksGETLists the long-running tasks the server tracks (space deletion, export, reindex) with their progress.

Search, 2 operations

searchSearchGETSearches Confluence with a CQL query across pages, blog posts, attachments, spaces and users, and returns each hit with a highlighted excerpt, its URL and when it was last modified.
search_contentSearch contentGETFinds content with a CQL query (for example space = DOCS and text ~ "invoice"), 25 results per page by default. Use expand to include bodies or versions.

Child, 1 operation

list_child_contentList child contentGETLists the direct children of a page of one type: page (child pages), comment or attachment.

Comment, 1 operation

list_commentsList commentsGETLists the comments of a page or blog post: top-level only by default, or every reply with depth=all, optionally only inline, footer or resolved ones. Comments carry authors' names.

Convert, 1 operation

convert_content_bodyConvert content bodyPOSTConverts a body from one representation to another: storage to view, export_view, styled_view or editor, or editor to storage. Returns the converted value.

Current, 1 operation

get_current_userGet current userGETReturns the user the credential belongs to: username, display name and profile picture.

Group, 1 operation

list_groupsList groupsGETLists the user groups of the Confluence server, 200 per page by default.

History, 1 operation

get_content_historyGet content historyGETReturns the history of a page or blog post: who created it and when, whether this is the latest version, and links to the previous and next versions.

Member, 1 operation

list_group_membersList group membersGETLists the users in a group (needs administrator permission). Personal data.

Memberof, 1 operation

list_user_groupsList user groupsGETLists the groups a user (by username or user key) belongs to.

Scan, 1 operation

scan_space_contentScan space contentGETLists every page or blog post of a space with cursor paging (pass nextCursor back as cursor), for exporting or indexing a large space.

Server information, 1 operation

get_server_informationGet server informationGETReturns the Confluence server's base URL, version, build number and build date.

User, 1 operation

get_userGet userGETReturns one user, found by username or by user key: display name, username, profile picture. Personal data.

Use Confluence Data Center from Claude Code, Cursor or Codex

Connect Confluence Data Center in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Confluence Data Center operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Confluence Data Center

Create your workspace
Sign up free. Nothing to install.
Connect Confluence Data Center once
Add your Confluence Data Center connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.