The Fleece AI Brain Jira connector syncs the issues from your connected Jira Cloud site into a local-first knowledge base — plain Markdown and SQLite on your own machine. Each issue's summary, description and status become a note titled by its key, and any MCP-compatible app such as Claude Desktop or Cursor can answer from your real Jira history in plain language, with the source one click away.
What syncs from Jira
Everything arrives as knowledge nodes — ordinary files you can open, link and search, not rows locked behind a JQL box.
Issues
Every issue from your connected Jira Cloud site that falls in the sync window, pulled through Jira's search API.
Summary & description
The summary and the description — Jira's rich ADF document flattened to clean plain text — become the note's title and body.
Status & project tags
Each note is tagged jira, status/<status> (e.g. status/InProgress) and project/<key> (e.g. project/ENG), so you can filter your brain by workflow state or project.
Titled by issue key
Notes are titled "ENG-123: summary", so a ticket reads the same in your brain as it does in Jira.
Incremental sync
Runs resume from a stored cursor (the newest updated timestamp) via JQL updated >= …; the first sync backfills the last 90 days rather than the whole project history.
Update-in-place & dedup
Keyed on the issue id, an edited issue refreshes its note in place and a re-sync never creates duplicates.
Connect Jira in four steps
No admin project, no automation rules — 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 Jira
In the app, open the connectors panel, choose Jira, and sign in with your Atlassian account. OAuth is brokered securely; your Jira content never passes through our servers.
- 03
It resolves your Jira site
The connector finds the Jira Cloud site your account can access and reads the issues on it — no cloud id or JQL 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 ticket decided, in plain English.
Jira remembers everything and answers in JQL.
Jira is the system of record for what your team is building, but getting an answer out of it means writing a query, then reading the ticket, then the description, then the linked ticket. The context that explains a decision is there — it is just spread across hundreds of issues no one reopens.
The Jira connector turns that record into memory you can ask. Every issue becomes a permanent note in one living knowledge graph, linked to the projects, statuses and work it relates to — so what ENG-412 actually decided is one plain-language question away.
Your tickets go from Jira to your disk. Nowhere else.
Authentication is a standard OAuth sign-in, but the actual sync calls the Jira Cloud REST API directly from the desktop app on your machine. Raw issues 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 Jira history, period. The files are yours, they open in Obsidian or any editor, and if you ever leave, you take everything with you.
- +Direct Jira-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
Ask your project history like a person.
One copy-paste connects the Brain to Claude Desktop, Cursor, Cline, Zed or agents you build. From then on, "what was the decision on the billing migration?" is answered from the actual ticket — no JQL, with the source note one click away.
Because every agent and tool reads the same graph, you stop re-explaining project context to each AI. On Teams, the organization map also shows which agents used that knowledge and what they cost.
Jira connector — FAQ
Does my Jira data pass through Fleece's servers?+
No. Sign-in uses a brokered OAuth flow, but the sync itself calls the Jira Cloud REST API directly from the desktop app on your machine. Raw issues land straight in your local vault; we never see or store your Jira content.
What exactly does the connector sync, and can I limit it?+
It syncs the issues your connected Jira account can see on one Jira Cloud site — each issue's summary, description and status. 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 Jira?+
No. The connector is read-only: it pulls issues into your knowledge base and never creates, transitions, comments on or edits anything in Jira.
How often does it sync, and does it refetch everything?+
Sync runs in the background and resumes from a stored cursor via a JQL updated filter, so each run only fetches recently changed issues; the first sync backfills the last 90 days. An edited issue refreshes its note in place, and a re-sync never creates duplicates.
Which plan do I need to connect Jira?+
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 Jira history?+
Connect the Brain to Claude Desktop, Cursor or any MCP-compatible app with a single copy-paste. Your AI then answers from the synced issues in plain language, citing the exact note it drew from.
Can I open the synced issues outside the app?+
Yes. Every issue 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 Jira?+
Sync stops, and everything already in your vault stays yours — the notes are local files, not a mirror that vanishes with the connection.
Stop writing JQL to reach your own decisions.
Connect Jira in one sign-in and let your whole AI stack answer from your project history in plain language.