Buildwithclaude confluence-automation
Automate Confluence page creation, content search, space management, labels, and hierarchy navigation via Rube MCP (Composio). Always search tools first for current schemas.
git clone https://github.com/davepoon/buildwithclaude
T=$(mktemp -d) && git clone --depth=1 https://github.com/davepoon/buildwithclaude "$T" && mkdir -p ~/.claude/skills && cp -r "$T/plugins/all-skills/skills/confluence-automation" ~/.claude/skills/davepoon-buildwithclaude-confluence-automation && rm -rf "$T"
plugins/all-skills/skills/confluence-automation/SKILL.mdConfluence Automation via Rube MCP
Automate Confluence operations including page creation and updates, content search with CQL, space management, label tagging, and page hierarchy navigation through Composio's Confluence toolkit.
Toolkit docs: composio.dev/toolkits/confluence
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Confluence connection via
with toolkitRUBE_MANAGE_CONNECTIONSconfluence - Always call
first to get current tool schemasRUBE_SEARCH_TOOLS
Setup
Get Rube MCP: Add
https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.
- Verify Rube MCP is available by confirming
respondsRUBE_SEARCH_TOOLS - Call
with toolkitRUBE_MANAGE_CONNECTIONSconfluence - If connection is not ACTIVE, follow the returned auth link to complete Confluence OAuth
- Confirm connection status shows ACTIVE before running any workflows
Core Workflows
1. Create and Update Pages
When to use: User wants to create new documentation or update existing Confluence pages
Tool sequence:
- List spaces to find the target space ID [Prerequisite]CONFLUENCE_GET_SPACES
- Find existing page to avoid duplicates or locate parent [Optional]CONFLUENCE_SEARCH_CONTENT
- Get current page content and version number before updating [Prerequisite for updates]CONFLUENCE_GET_PAGE_BY_ID
- Create a new page in a space [Required for creation]CONFLUENCE_CREATE_PAGE
- Update an existing page with new content and incremented version [Required for updates]CONFLUENCE_UPDATE_PAGE
- Tag the page with labels after creation [Optional]CONFLUENCE_ADD_CONTENT_LABEL
Key parameters:
: Space ID or key (e.g.,spaceId
,"DOCS"
) -- space keys are auto-converted to IDs"12345678"
: Page title (must be unique within a space)title
: Parent page ID for creating child pages; omit to place under space homepageparentId
: HTML/XHTML content in Confluence storage formatbody.storage.value
: Must bebody.storage.representation
for create operations"storage"
: For updates, must be current version + 1version.number
: Optional change descriptionversion.message
Pitfalls:
- Confluence enforces unique page titles per space; creating a page with a duplicate title will fail
requiresUPDATE_PAGE
set to current version + 1; always fetch current version first withversion.numberGET_PAGE_BY_ID- Content must be in Confluence storage format (XHTML), not plain text or Markdown
usesCREATE_PAGE
whilebody.storage.value
usesUPDATE_PAGE
withbody.valuebody.representation
requires a numeric long ID, not a UUID or stringGET_PAGE_BY_ID
2. Search Content
When to use: User wants to find pages, blog posts, or content across Confluence
Tool sequence:
- Keyword search with intelligent relevance ranking [Required]CONFLUENCE_SEARCH_CONTENT
- Advanced search using Confluence Query Language [Alternative]CONFLUENCE_CQL_SEARCH
- Hydrate full content for selected search results [Optional]CONFLUENCE_GET_PAGE_BY_ID
- Browse pages sorted by date when search relevance is weak [Fallback]CONFLUENCE_GET_PAGES
Key parameters for SEARCH_CONTENT:
: Search text matched against page titles with intelligent rankingquery
: Limit search to a specific spacespaceKey
: Max results (default 25, max 250)limit
: Pagination offset (0-based)start
Key parameters for CQL_SEARCH:
: CQL query string (e.g.,cql
)text ~ "API docs" AND space = DOCS AND type = page
: Comma-separated properties (e.g.,expand
,content.space
)content.body.storage
:excerpt
,highlight
, orindexednone
: Max results (max 250; reduced to 25-50 when using body expansions)limit
CQL operators and fields:
- Fields:
,text
,title
,label
,space
,type
,creator
,lastModified
,createdancestor - Operators:
,=
,!=
(contains),~
,!~
,>
,<
,>=
,<=
,INNOT IN - Functions:
,currentUser()
,now("-7d")now("-30d") - Example:
title ~ "meeting" AND lastModified > now("-7d") ORDER BY lastModified DESC
Pitfalls:
fetches up to 300 pages and applies client-side filtering -- not a true full-text searchCONFLUENCE_SEARCH_CONTENT
is the real full-text search; useCONFLUENCE_CQL_SEARCH
for content body searchtext ~ "term"- HTTP 429 rate limits can occur; throttle to ~2 requests/second with backoff
- Using body expansions in CQL_SEARCH may reduce max results to 25-50
- Search indexing is not immediate; recently created pages may not appear
3. Manage Spaces
When to use: User wants to list, create, or inspect Confluence spaces
Tool sequence:
- List all spaces with optional filtering [Required]CONFLUENCE_GET_SPACES
- Get detailed metadata for a specific space [Optional]CONFLUENCE_GET_SPACE_BY_ID
- Create a new space with key and name [Optional]CONFLUENCE_CREATE_SPACE
- Retrieve custom metadata stored as space properties [Optional]CONFLUENCE_GET_SPACE_PROPERTIES
- List pages, blog posts, or attachments in a space [Optional]CONFLUENCE_GET_SPACE_CONTENTS
- List labels on a space [Optional]CONFLUENCE_GET_LABELS_FOR_SPACE
Key parameters:
: Space key -- alphanumeric only, no underscores or hyphens (e.g.,key
,DOCS
)PROJECT1
: Human-readable space namename
:type
orglobalpersonal
:status
(active) orcurrentarchived
: For GET_SPACE_CONTENTS, filters by space keyspaceKey
: Numeric space ID for GET_SPACE_BY_ID (NOT the space key)id
Pitfalls:
- Space keys must be alphanumeric only (no underscores, hyphens, or special characters)
requires numeric space ID, not the space key; useGET_SPACE_BY_ID
to find numeric IDsGET_SPACES- Clickable space URLs may need assembly: join
(relative) with_links.webui_links.base - Default pagination is 25; set
explicitly (max 200 for spaces)limit
4. Navigate Page Hierarchy and Labels
When to use: User wants to explore page trees, child pages, ancestors, or manage labels
Tool sequence:
- Find the target page ID [Prerequisite]CONFLUENCE_SEARCH_CONTENT
- List direct children of a parent page [Required]CONFLUENCE_GET_CHILD_PAGES
- Get the full ancestor chain for a page [Optional]CONFLUENCE_GET_PAGE_ANCESTORS
- List labels on a specific page [Optional]CONFLUENCE_GET_LABELS_FOR_PAGE
- Add labels to a page [Optional]CONFLUENCE_ADD_CONTENT_LABEL
- List labels across all content in a space [Optional]CONFLUENCE_GET_LABELS_FOR_SPACE_CONTENT
- Audit edit history for a page [Optional]CONFLUENCE_GET_PAGE_VERSIONS
Key parameters:
: Page ID for child pages, ancestors, labels, and versionsid
: Opaque pagination cursor for GET_CHILD_PAGES (fromcursor
)_links.next
: Items per page (max 250 for child pages)limit
: Child page sort options:sort
,id
,-id
,created-date
,-created-date
,modified-date
,-modified-date
,child-position-child-position
Pitfalls:
only returns direct children, not nested descendants; recurse for full treeGET_CHILD_PAGES- Pagination for GET_CHILD_PAGES uses cursor-based pagination (not start/limit)
- Verify the correct page ID from search before using as parent; search can return similar titles
requires the page ID, not a version numberGET_PAGE_VERSIONS
Common Patterns
ID Resolution
Always resolve human-readable names to IDs before operations:
- Space key -> Space ID:
withCONFLUENCE_GET_SPACES
filter, orspaceKey
accepts space keys directlyCREATE_PAGE - Page title -> Page ID:
withCONFLUENCE_SEARCH_CONTENT
param, then extract page IDquery - Space ID from URL: Extract numeric ID from Confluence URLs or use GET_SPACES
Pagination
Confluence uses two pagination styles:
- Offset-based (most endpoints):
(0-based offset) +start
(page size). Incrementlimit
bystart
until fewer results thanlimit
are returned.limit - Cursor-based (GET_CHILD_PAGES, GET_PAGES): Use the
fromcursor
in the response. Continue until no_links.next
link is present.next
Content Formatting
- Pages use Confluence storage format (XHTML), not Markdown
- Basic elements:
,<p>
-<h1>
,<h6>
,<strong>
,<em>
,<code>
,<ul>
,<ol><li> - Tables:
/<table><tbody><tr><th>
structure<td> - Macros:
for code blocks, etc.<ac:structured-macro ac:name="code"> - Always wrap content in proper XHTML tags
Known Pitfalls
ID Formats
- Space IDs are numeric (e.g.,
); space keys are short strings (e.g.,557060
)DOCS - Page IDs are numeric long values for GET_PAGE_BY_ID; some tools accept UUID format
requires numeric ID, not the space keyGET_SPACE_BY_ID
takes an integer, not a stringGET_PAGE_BY_ID
Rate Limits
- HTTP 429 can occur on search endpoints; honor Retry-After header
- Throttle to ~2 requests/second with exponential backoff and jitter
- Body expansion in CQL_SEARCH reduces result limits to 25-50
Content Format
- Content must be Confluence storage format (XHTML), not Markdown or plain text
- Invalid XHTML will cause page creation/update to fail
nests body underCREATE_PAGE
;body.storage.value
usesUPDATE_PAGE
+body.valuebody.representation
Version Conflicts
- Updates require exact next version number (current + 1)
- Concurrent edits can cause version conflicts; always fetch current version immediately before updating
- Title changes during update must still be unique within the space
Quick Reference
| Task | Tool Slug | Key Params |
|---|---|---|
| List spaces | | , , |
| Get space by ID | | |
| Create space | | , , |
| Space contents | | , , |
| Space properties | | , |
| Search content | | , , |
| CQL search | | , , |
| List pages | | , , |
| Get page by ID | | (integer) |
| Create page | | , , |
| Update page | | , , , |
| Delete page | | |
| Child pages | | , , |
| Page ancestors | | |
| Page labels | | |
| Add label | | content ID, label |
| Page versions | | |
| Space labels | | space ID |
Powered by Composio