Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Automate Confluence page creation, content search, space management, labels, and hierarchy navigation via Rube MCP (Composio). Always search tools first for current schemas.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-10 | ✗→✓ | ▲ Improved | 143% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 345% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 81% | 0% |
| case-20 | ✗→✓ | ▲ Improved | 546% | 0% |
| case-05 | ✓→✗ | ▼ Worse | 117% | 0% |
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
RUBE_MANAGE_CONNECTIONS with toolkit confluenceRUBE_SEARCH_TOOLS first to get current tool schemasGet 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.
RUBE_SEARCH_TOOLS respondsRUBE_MANAGE_CONNECTIONS with toolkit confluenceWhen to use: User wants to create new documentation or update existing Confluence pages
Tool sequence:
CONFLUENCE_GET_SPACES - List spaces to find the target space ID Prerequisite]CONFLUENCE_SEARCH_CONTENT - Find existing page to avoid duplicates or locate parent Optional]CONFLUENCE_GET_PAGE_BY_ID - Get current page content and version number before updating Prerequisite for updates]CONFLUENCE_CREATE_PAGE - Create a new page in a space Required for creation]CONFLUENCE_UPDATE_PAGE - Update an existing page with new content and incremented version Required for updates]CONFLUENCE_ADD_CONTENT_LABEL - Tag the page with labels after creation Optional]Key parameters:
spaceId: Space ID or key (e.g., "DOCS", "12345678") -- space keys are auto-converted to IDstitle: Page title (must be unique within a space)parentId: Parent page ID for creating child pages; omit to place under space homepagebody.storage.value: HTML/XHTML content in Confluence storage formatbody.storage.representation: Must be "storage" for create operationsversion.number: For updates, must be current version + 1version.message: Optional change descriptionPitfalls:
UPDATE_PAGE requires version.number set to current version + 1; always fetch current version first with GET_PAGE_BY_IDCREATE_PAGE uses body.storage.value while UPDATE_PAGE uses body.value with body.representationGET_PAGE_BY_ID requires a numeric long ID, not a UUID or stringWhen to use: User wants to find pages, blog posts, or content across Confluence
Tool sequence:
CONFLUENCE_SEARCH_CONTENT - Keyword search with intelligent relevance ranking Required]CONFLUENCE_CQL_SEARCH - Advanced search using Confluence Query Language Alternative]CONFLUENCE_GET_PAGE_BY_ID - Hydrate full content for selected search results Optional]CONFLUENCE_GET_PAGES - Browse pages sorted by date when search relevance is weak Fallback]Key parameters for SEARCH_CONTENT:
query: Search text matched against page titles with intelligent rankingspaceKey: Limit search to a specific spacelimit: Max results (default 25, max 250)start: Pagination offset (0-based)Key parameters for CQL_SEARCH:
cql: CQL query string (e.g., text ~ "API docs" AND space = DOCS AND type = page)expand: Comma-separated properties (e.g., content.space, content.body.storage)excerpt: highlight, indexed, or nonelimit: Max results (max 250; reduced to 25-50 when using body expansions)CQL operators and fields:
text, title, label, space, type, creator, lastModified, created, ancestor=, !=, ~ (contains), !~, >, <, >=, <=, IN, NOT INcurrentUser(), now("-7d"), now("-30d")title ~ "meeting" AND lastModified > now("-7d") ORDER BY lastModified DESCPitfalls:
CONFLUENCE_SEARCH_CONTENT fetches up to 300 pages and applies client-side filtering -- not a true full-text searchCONFLUENCE_CQL_SEARCH is the real full-text search; use text ~ "term" for content body searchWhen to use: User wants to list, create, or inspect Confluence spaces
Tool sequence:
CONFLUENCE_GET_SPACES - List all spaces with optional filtering Required]CONFLUENCE_GET_SPACE_BY_ID - Get detailed metadata for a specific space Optional]CONFLUENCE_CREATE_SPACE - Create a new space with key and name Optional]CONFLUENCE_GET_SPACE_PROPERTIES - Retrieve custom metadata stored as space properties Optional]CONFLUENCE_GET_SPACE_CONTENTS - List pages, blog posts, or attachments in a space Optional]CONFLUENCE_GET_LABELS_FOR_SPACE - List labels on a space Optional]Key parameters:
key: Space key -- alphanumeric only, no underscores or hyphens (e.g., DOCS, PROJECT1)name: Human-readable space nametype: global or personalstatus: current (active) or archivedspaceKey: For GET_SPACE_CONTENTS, filters by space keyid: Numeric space ID for GET_SPACE_BY_ID (NOT the space key)Pitfalls:
GET_SPACE_BY_ID requires numeric space ID, not the space key; use GET_SPACES to find numeric IDs_links.webui (relative) with _links.baselimit explicitly (max 200 for spaces)When to use: User wants to explore page trees, child pages, ancestors, or manage labels
Tool sequence:
CONFLUENCE_SEARCH_CONTENT - Find the target page ID Prerequisite]CONFLUENCE_GET_CHILD_PAGES - List direct children of a parent page Required]CONFLUENCE_GET_PAGE_ANCESTORS - Get the full ancestor chain for a page Optional]CONFLUENCE_GET_LABELS_FOR_PAGE - List labels on a specific page Optional]CONFLUENCE_ADD_CONTENT_LABEL - Add labels to a page Optional]CONFLUENCE_GET_LABELS_FOR_SPACE_CONTENT - List labels across all content in a space Optional]CONFLUENCE_GET_PAGE_VERSIONS - Audit edit history for a page Optional]Key parameters:
id: Page ID for child pages, ancestors, labels, and versionscursor: Opaque pagination cursor for GET_CHILD_PAGES (from _links.next)limit: Items per page (max 250 for child pages)sort: Child page sort options: id, -id, created-date, -created-date, modified-date, -modified-date, child-position, -child-positionPitfalls:
GET_CHILD_PAGES only returns direct children, not nested descendants; recurse for full treeGET_PAGE_VERSIONS requires the page ID, not a version numberAlways resolve human-readable names to IDs before operations:
CONFLUENCE_GET_SPACES with spaceKey filter, or CREATE_PAGE accepts space keys directlyCONFLUENCE_SEARCH_CONTENT with query param, then extract page IDConfluence uses two pagination styles:
start (0-based offset) + limit (page size). Increment start by limit until fewer results than limit are returned.cursor from _links.next in the response. Continue until no next link is present.<p>, <h1>-<h6>, <strong>, <em>, <code>, <ul>, <ol>, <li><table><tbody><tr><th> / <td> structure<ac:structured-macro ac:name="code"> for code blocks, etc.557060); space keys are short strings (e.g., DOCS)GET_SPACE_BY_ID requires numeric ID, not the space keyGET_PAGE_BY_ID takes an integer, not a stringCREATE_PAGE nests body under body.storage.value; UPDATE_PAGE uses body.value + body.representation| Task | Tool Slug | Key Params | |------|-----------|------------| | List spaces | CONFLUENCE_GET_SPACES | type, status, limit | | Get space by ID | CONFLUENCE_GET_SPACE_BY_ID | id | | Create space | CONFLUENCE_CREATE_SPACE | key, name, type | | Space contents | CONFLUENCE_GET_SPACE_CONTENTS | spaceKey, type, status | | Space properties | CONFLUENCE_GET_SPACE_PROPERTIES | id, key | | Search content | CONFLUENCE_SEARCH_CONTENT | query, spaceKey, limit | | CQL search | CONFLUENCE_CQL_SEARCH | cql, expand, limit | | List pages | CONFLUENCE_GET_PAGES | spaceId, sort, limit | | Get page by ID | CONFLUENCE_GET_PAGE_BY_ID | id (integer) | | Create page | CONFLUENCE_CREATE_PAGE | title, spaceId, body | | Update page | CONFLUENCE_UPDATE_PAGE | id, title, body, version | | Delete page | CONFLUENCE_DELETE_PAGE | id | | Child pages | CONFLUENCE_GET_CHILD_PAGES | id, limit, sort | | Page ancestors | CONFLUENCE_GET_PAGE_ANCESTORS | id | | Page labels | CONFLUENCE_GET_LABELS_FOR_PAGE | id | | Add label | CONFLUENCE_ADD_CONTENT_LABEL | content ID, label | | Page versions | CONFLUENCE_GET_PAGE_VERSIONS | id | | Space labels | CONFLUENCE_GET_LABELS_FOR_SPACE | space ID |
Powered by Composio
Other measured skills in the registry, with their headline benchmark lift.