mcp-jira·integration·active

Jira MCP

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

TARA ARIAtrigger · mcp⌘ MCP · Atlassian

Jira MCP

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

What flows in

·Sprint metadata (name, dates, goal, participants)

·User stories with descriptions, acceptance criteria, attachments

·Linked Confluence pages (via Atlassian's cross-product link)

·Issue history (state transitions, comments)

·Custom fields (story points, components, labels)

What flows out

·New issues created from ARIA recommendations

·Comments on existing issues with SARA findings

·Status transitions when a finding is remediated

·Sprint-review summary posts

Authentication

OAuth 2.0 (3LO) flow. The first time the connector is used, it walks the user through Atlassian consent. Tokens are stored encrypted and refreshed automatically.

→The connector requests the minimum scopes required: read:jira-work, write:jira-work, read:sprint:jira-software, write:sprint:jira-software. Admin scopes are never requested.

JQL support

For complex queries (e.g."all bugs labeled regression in the last 6 sprints"), the connector accepts raw JQL. ARIA uses this forTrend Detector historical loads.

Rate limiting

Atlassian rate limits are respected globally — the connector tracks remaining quota and backs off proactively. Bulk operations are batched to stay under per-minute caps.

Field mapping

Custom fields differ across orgs (customfield_10001 etc.). The connector auto-discovers field metadata on first use and asks the engineer once to map:

·Story points field

·Sprint field (usually customfield_10020)

·Epic link

·Severity / priority

The mapping is cached per Jira instance.

Audit

Every write operation goes through a trail:

·Who triggered it (which agent, which user)

·When it ran

·What changed

·A link back to the ARIA run that motivated the write

This trail lives in Jira itself as a comment or property, so audit isn't dependent on the connector being available.

Server URL

mcp://jira.atlassian.com

→For Jira Server / Data Center installations, the URL is configured per-instance with a path to the on-prem MCP gateway.

MCP server endpoint

mcp://jira.atlassian.com/sse

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.

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.

Confluence MCP

mcp-confluence

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

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.