It would be amazing if I could have Claude etc generate diagrams (say SVGs) and upload/insert them into generated documentation using the MCP server. At the moment I have to manually copy and paste them in which breaks down the amazing benefits from using confluence and the mcp server for docs. I love the connector btw :)
I believe current Confluence MCP servers rely on standard REST API v2 endpoints for reading and writing Confluence Storage Format (XML/HTML) text content.
Uploading and displaying visuals involves a two-step process that most standard MCP implementations don't combine into a single tool yet.
Looks like a feature request is open for this https://jira.atlassian.com/browse/ECO-1265
GitHub reference specifically requests tools (getConfluencePageAttachments, uploadConfluenceAttachment) to fetch and upload media natively without needing external scripts.
I've been struggling with this whole week... 😅
I mean, it's not that bad, but it can get quite annoying when you have to add/copy attachments manually.
Anyhow, as Viswanathan said, ECO-1265 is a place to look at > I'd recommend setting yourself as a watcher. I do believe they've mentioned somewhere that this should be shipped this or next quarter, but we'll see. 👀
It will definitelly save a lot of time in some cases.
Cheers,
Tobi
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.
Welcome to the community !!
As Vishwa suggest a mktplace app can help to render mermaid diagrams directly in Confluence. If you are open to try out one, take a look at
Mermaid Diagrams & Charts for Confluence
The app has more than 15 diagramming templates and also integrates with your code repositories like GitHub/Bitbucket.
Disclaimer : I am part of the app dev team
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.