mcp-confluence·integration·active

Confluence MCP

Reads PRDs and ACs from Confluence pages as TARA input. Publishes ARIA's quality reports back as Confluence pages with embedded charts.

TARA ARIAtrigger · mcp⌘ MCP · Atlassian

Confluence MCP

Reads PRDs and acceptance criteria from Confluence pages as TARA input. Publishes ARIA's quality reports back as Confluence pages with embedded charts.

What flows in

·Page content (rich text → markdown for TARA's consumption)

·Page hierarchy (spaces, parent/child)

·Page version history (so re-runs see only the changes)

·Linked Jira issues (Atlassian cross-product links)

What flows out

·New pages with ARIA reports (one page per sprint, child of the team space)

·Updates to existing pages (e.g. sprint review pages with ARIA results appended)

·Page properties (sprint metadata, agent run IDs) for queryability later

Page identification

Pages are identified by:

·URL — the connector accepts full Confluence URLs

·Title + space — the connector resolves these for natural-language references

·Page ID — for direct programmatic access

Renamed pages are tracked by ID, so a TARA run that pulled "Login Requirements v3" still works after the page is renamed.

Markdown conversion

Confluence stores content in its own XHTML-based format. The connector converts to Markdown for TARA, preserving:

·Headings + lists

·Tables (with rough Markdown table fidelity)

·Code blocks

·Links (internal + external)

·Inline images (referenced, not embedded)

→Macros (panel, info, warning) are converted to blockquotes with a marker. Custom macros are surfaced as a comment so the engineer can add them to the conversion rules.

Quality report rendering

When ARIA publishes a report back to Confluence:

·Charts are rendered as PNG and uploaded as attachments

·Tables are converted to Confluence table macros

·Trend lines are rendered with theChart from Table macro for interactivity

·Page tree placement is configurable: by sprint, by team, or by release

The page is created with a property aria.run_id so future ARIA runs can find and update it instead of creating duplicates.

Authentication

OAuth 2.0 (Atlassian, shared with the Jira MCP). When both are connected, they share refresh tokens.

Server

mcp://confluence.atlassian.com

Vendor

Atlassian.

Privacy + scope

→The connector reads only spaces it's been explicitly granted access to. Org-wide read scope is refused — engineers configure per-space access on first use.

MCP server endpoint

mcp://confluence.atlassian.com

vendor · Atlassian

Related · integration

Sprint Context Loader

sprint-context-loader

Pulls sprint metadata — name, dates, team, release tag, prior trend data — directly from connected issue trackers via MCP.

Jira MCP

mcp-jira

Bidirectional Jira connector. TARA pulls stories from sprints; ARIA pushes findings, recommendations, and quality reports back as issues, comments, or sprint reviews.

TestRail MCP

mcp-testrail

Pulls existing test cases and execution history; pushes EVAN-generated tests and run results back as cases, runs, and milestone reports.

Azure DevOps MCP

mcp-ado

Pulls work items + repos; pushes test plans, suites, and runs. Handles ADO test points and outcome states with full bi-directional sync.

GitHub MCP

mcp-github

Reads PRs, issues, code search; opens PRs containing EVAN-generated automation, SARA remediation patches, and ARIA-recommended changes.

Slack MCP

mcp-slack

Real-time notifications when SARA finds Critical issues, LEO breaches an SLO, or ARIA's trend detector flags a regression. Routed to the right channel by component.