The Fleece AI Brain Confluence connector syncs the pages from your connected Confluence Cloud site into a local-first knowledge base — plain Markdown and SQLite on your own machine. Each page becomes a note titled by its page title, its body converted to clean text, and any MCP-compatible app such as Claude Desktop or Cursor can answer from your real wiki, with the source one click away.
What syncs from Confluence
Everything arrives as knowledge nodes — ordinary files you can open, link and search, not pages buried in a space no one opens.
Pages
Every page your connected Confluence account can access on the site, pulled through the Confluence Cloud v2 pages API.
Page body as text
The page's storage-format body is stripped from XHTML to clean plain text, so the content reads cleanly in your vault and in search.
Titled by page
Each note keeps the page title (or "Untitled Confluence page" when a page has none) and is tagged confluence.
Version-aware updates
Each page maps to one note keyed on its version timestamp; a page edited upstream refreshes its note in place, and an unchanged page is a cheap skip.
Newest-first, incremental
Runs walk pages newest-modified-first and stop at the version cursor they last reached; a first run captures the whole space, later runs only touch what changed.
Connect Confluence in four steps
No space admin, no export job — one sign-in from the desktop app.
- 01
Install Fleece AI Brain
Download the desktop app for macOS, Windows or Linux and open your vault — a folder of plain Markdown files on your machine.
- 02
Open Connectors and pick Confluence
In the app, open the connectors panel, choose Confluence, and sign in with your Atlassian account. OAuth is brokered securely; your Confluence content never passes through our servers.
- 03
It resolves your Confluence site
The connector finds the Confluence Cloud site your account can access and reads the pages on it — no cloud id or space keys to configure by hand.
- 04
Let it sync — then ask
Sync runs in the background and stays up to date. Point Claude Desktop, Cursor or any MCP app at your Brain and ask what a runbook or spec actually says.
Confluence is where documentation goes to be forgotten.
Someone wrote the runbook, the architecture decision, the onboarding guide — once. Then it sank under a hundred other pages, the search never quite surfaced it, and the team went back to asking in chat. Written once, findable never.
The Confluence connector turns the wiki back into knowledge you reach for. Every page becomes a permanent note in one living knowledge graph, linked to the work it documents — so the spec written in a space you forgot exists is still one question away.
Your pages go from Confluence to your disk. Nowhere else.
Authentication is a standard OAuth sign-in, but the actual sync calls the Confluence Cloud REST API directly from the desktop app on your machine. Raw pages never transit Fleece's servers or any third party — they land straight in your vault as Markdown and SQLite.
That is the whole trust model: we can't read your wiki, period. The files are yours, they open in Obsidian or any editor, and if you ever leave, you take everything with you.
- +Direct Confluence-to-device sync — raw payloads never touch our servers
- +Vault = plain .md files + SQLite, 100% Obsidian-compatible
- +Works offline once synced; cloud sync is optional and end-to-end encrypted
Make your documentation answer questions.
One copy-paste connects the Brain to Claude Desktop, Cursor, Cline, Zed or agents you build. From then on, "what's our incident escalation process?" is answered from the actual page — with the source note one click away.
Because every agent and tool reads the same graph, your documentation finally does its job without anyone reopening Confluence. On Teams, the organization map also shows which agents used that knowledge and what they cost.
Confluence connector — FAQ
Does my Confluence data pass through Fleece's servers?+
No. Sign-in uses a brokered OAuth flow, but the sync itself calls the Confluence Cloud REST API directly from the desktop app on your machine. Raw pages land straight in your local vault; we never see or store your Confluence content.
What exactly does the connector sync, and can I limit it?+
It syncs the pages your connected Confluence account can access on one Confluence Cloud site, converting each page body to plain text. You limit the scope by choosing which Atlassian account and site you connect; nothing outside that site is read.
Does it write anything back to Confluence?+
No. The connector is read-only: it pulls pages into your knowledge base and never creates, edits or deletes anything in your wiki.
How often does it sync, and does it refetch everything?+
Sync runs in the background, walking pages newest-modified-first and stopping at the version it last reached, so only changed pages are re-ingested; a page edited upstream refreshes its note in place. The first run captures the whole space; later runs are incremental.
Which plan do I need to connect Confluence?+
The local brain is free, and connectors are the paid lever: Solo (€12/month) includes up to 3 connected tools, Pro (€24/month) makes them unlimited with auto-sync. Every plan starts with a 14-day trial, no card required.
How do I ask Claude or Cursor about my wiki?+
Connect the Brain to Claude Desktop, Cursor or any MCP-compatible app with a single copy-paste. Your AI then answers from the synced pages, citing the exact note it drew from.
Can I open the synced pages outside the app?+
Yes. Every page is an ordinary Markdown file in your vault, fully Obsidian-compatible — open, edit or grep them with any tool, and take them with you if you ever leave.
What happens if I disconnect Confluence?+
Sync stops, and everything already in your vault stays yours — the notes are local files, not a mirror that vanishes with the connection.
Stop letting documentation go to be forgotten.
Connect Confluence in one sign-in and turn a wiki no one reopens into memory your whole AI stack can reach.