Licensed to be used in conjunction with basebox, only.
// integration
Atlassian Confluence
Applies to
Product: Cloud · Server · Audience: Administrator
The Atlassian Confluence connector lets the basebox assistant search, read, create, change, move and delete pages in Confluence. It works with Atlassian Cloud and with Confluence Server / Data Center. Jira has its own connector, Atlassian Jira, because the two products can live on different servers.
What does the connector do?
This and the following sections are generated from the information the connector's image carries. What applies to every connector is described under What applies to every connector.
In the catalog it describes itself as:
Search, read and edit Confluence pages.
It gives the assistant these instructions:
Confluence, seen with the user's own account: absent results can mean 'not permitted' as well as 'not there'. Find pages with confluence_search, then read one with confluence_get_page. Change one section of a page with confluence_update_page_section rather than replacing the whole page. Ask before deleting anything.
Settings
The administrator fills in these fields in the connector's settings. They apply to the whole organisation.
| Field | Required | Meaning |
|---|---|---|
| Confluence URL | no | On Atlassian Cloud the site address followed by /wiki; on Server/Data Center the Confluence web root. Example: https://acme.atlassian.net/wiki |
| Help links for signing in | no | One link per sign-in method, e.g. a page on your intranet explaining how to create an API token. |
Sign-in
The administrator decides how the connector signs in: with Personal sign-in each person signs in with their own account and sees only what they may. With Company account everyone uses one account the administrator enters.
Personal sign-in
- Email and API token (Atlassian Cloud) – asks for a username and password. Create an API token at id.atlassian.com → Security → API tokens.
- Personal access token (Server / Data Center) – asks for a token. Create one in Confluence under your profile → Settings → Personal Access Tokens.
Company account
- Service account's email and API token (Atlassian Cloud) – asks for a username and password. A dedicated Atlassian account with access to what every user may see.
- Service account's personal access token (Server / Data Center) – asks for a token.
A company account gives everyone the same rights
Every basebox user reaches the system with the rights of this one account. Results are not trimmed to what each person may see.
The connector adds:
Every basebox user sees the pages this one account can see, and every comment or change they make is recorded under its name.
Tools
The assistant can call 15 tools.
| Tool | Effect | Description |
|---|---|---|
check_connection |
reads | Checks that the user's Confluence credential is accepted and returns the signed-in user. |
confluence_copy_page |
writes | Copies a Confluence page under a new title into a space, optionally below a parent page; on Cloud attachments are copied too unless declined. |
confluence_create_page |
writes | Creates a Confluence page in a space, optionally below a parent page, from a body in Confluence storage format (XHTML) or wiki markup, optionally with a title emoji, a layout width or as a Live Doc (Cloud), and returns it with its id and web link. |
confluence_delete_page |
modifies or deletes | Deletes a Confluence page, moving it to the space's trash. |
confluence_get_page |
reads | Reads one Confluence page by its id, URL or tiny link, or by its title in a space, with its text as Markdown (or raw storage format), its title, space, version, parent pages and labels. The result says whether the text was truncated. |
confluence_get_page_children |
reads | Lists the pages, and by default the folders, directly below a Confluence page, one page of results at a time, optionally with each child page's text. |
confluence_get_page_diff |
reads | Compares two versions of a Confluence page and returns a unified diff of their text as Markdown. |
confluence_get_page_history |
reads | Reads an earlier version of a Confluence page by version number, with its text as Markdown (or raw storage format) and that version's author and date. |
confluence_get_page_restrictions |
reads | Shows which users and groups may view and which may edit a Confluence page; empty lists mean the page is not restricted. |
confluence_get_space_page_tree |
reads | Lists the pages of a Confluence space as a flat list of id, title, parent id, position and depth, to see how the space is organised before creating or moving pages. |
confluence_move_page |
modifies or deletes | Moves a Confluence page below or next to another page, or to another space below its home page, and returns the page with its new parent pages. |
confluence_search |
reads | Searches Confluence with plain search terms or a CQL query and returns one page of results, each with its title, an excerpt, its space and the content id to read it by. |
confluence_set_page_restrictions |
modifies or deletes | Replaces the view and edit restrictions of a Confluence page with the given users and groups; lists left out or empty lift that restriction. |
confluence_update_page |
modifies or deletes | Replaces the whole body of a Confluence page with new content in Confluence storage format (XHTML) or wiki markup as a new page version, optionally renaming it, moving it below another page or changing its title emoji or layout width. |
confluence_update_page_section |
modifies or deletes | Replaces the body of one section of a Confluence page, the content under a given heading up to the next heading of the same or a higher level, with new content in storage format (XHTML), leaving the rest of the page untouched. |
Generated from mcp-atlassian-confluence:v0.2.1.