Atlassian Cloud (Jira, Confluence, Compass) is where many engineering and product teams plan, document, and ship work. The Atlassian hosted MCP server brings that data into your clariBI AI analyses without per-tool integrations.
Why connect Atlassian
Engineering velocity questions usually require pulling Jira filters, cross-referencing sprint history, and reading Confluence design docs. Each is a manual step.
With Atlassian connected to clariBI, you can ask "What is our average issue cycle time in the platform team?", "Find all bugs without an owner", or "Summarize the onboarding runbook in Confluence" and the AI engine routes to the right tool.
How the connection works
clariBI talks to Atlassian through its hosted MCP server at https://mcp.atlassian.com/v1/sse. Authentication uses an OAuth flow that clariBI registers itself for (no developer console setup on your side). Tokens stay encrypted server-side and never leave clariBI in clear form.
sequenceDiagram
actor U as You
participant C as clariBI
participant V as Atlassian
U->>C: Click Authorize with Atlassian
C->>V: Open OAuth authorization
V-->>U: Grant read access?
U->>V: Approve
V-->>C: Authorization code
C->>V: Exchange code for tokens
V-->>C: Access + refresh tokens
C->>C: Encrypt and store credentials
C-->>U: Connection ready
Available tools
clariBI exposes the read-only Atlassian tools that the vendor's MCP server publishes at connection time. Write operations (create, update, delete, send, refund) are filtered out by a name-pattern blocklist before any tool reaches the analysis engine, so connecting Atlassian cannot modify data on the vendor side.
The exact tool inventory depends on the Atlassian features your account has access to. After connecting, try a few natural-language questions to see what Atlassian data clariBI can pull.
Data flow during analysis
When you ask a question that maps to Atlassian, the AI engine routes to the right tool, reads the result, and pairs the answer with a chart you can pin to a dashboard.
sequenceDiagram
actor U as You
participant C as clariBI
participant AI as AI engine
participant V as Atlassian
U->>C: Ask a question about engineering and documentation data
C->>AI: Plan the analysis
AI->>V: Call the right tool
V-->>AI: Tool result
AI->>AI: Summarize and chart
C-->>U: Answer plus visual
Setting up the connection
- Open Data Sources in the clariBI sidebar.
- Click Add data source.
- Open the MCP Servers tab.
- Click the Atlassian card.
- Click Authorize with Atlassian.
- Sign in to Atlassian in the popup window and grant the requested read scopes.
- Back in clariBI, give your data source a name.
- Click Finish.
Permissions and data access
clariBI requests read access to Jira issues and projects, Confluence pages and spaces, and Compass components. No issues, pages, or transitions can be modified. Disconnect from Atlassian account settings or from clariBI Settings.
Troubleshooting
| Error | Cause | Fix |
|---|---|---|
| "Selected Jira site not accessible" | Your Atlassian session is for an organization you no longer have access to. | Sign in to the right Atlassian organization in another tab, then reconnect. |
| "JQL syntax error" in analysis | A natural-language question was translated to invalid JQL. | Rephrase your question with more specific filter language (project, status, or assignee). |