Confluence-MCP is a server implementation that provides AI assistants with direct access to Atlassian Confluence wikis. Built with TypeScript and Bun, it offers tools for retrieving, searching, creating, and updating Confluence pages through a clean interface. The server handles authentication via API tokens, transforms Confluence's storage format content into both plain text and markdown, and optimizes content for AI context windows. It includes robust error handling and content cleaning utilities, making it particularly valuable for teams who want to query and manage their knowledge base directly through AI assistants without switching contexts.
暂无评论. 成为第一个评论的人！
登录以参与讨论
Retrieve a Confluence page by ID. Parameters: pageId (string), format (string - 'text' or 'markdown'), includeMarkup (boolean)
Search for Confluence pages using CQL (Confluence Query Language). Parameters: query (string), limit (integer), format (string - 'text' or 'markdown'), includeMarkup (boolean)
List all available Confluence spaces. Parameters: limit (integer)
Create a new Confluence page. Parameters: spaceKey (string), title (string), content (string - XHTML), parentId (optional string)
Update an existing Confluence page. Parameters: pageId (string), title (string), content (string - XHTML), version (integer)
Retrieve comments for a specific Confluence page. Parameters: pageId (string), limit (integer), format (string - 'text' or 'markdown')
Add a comment to a Confluence page. Parameters: pageId (string), content (string - XHTML), parentId (optional string)
Retrieve attachments for a specific Confluence page. Parameters: pageId (string), limit (integer)
Add an attachment to a Confluence page. Parameters: pageId (string), filename (string), fileContentBase64 (string), comment (string)
