How to pull Jira data into Worklayer

Use Case: When you need sprint summaries, bug lists, or issue details from Jira for reports or planning Time to Complete: 2 minutes Prerequisites: Jira connected via MCP Manager

Quick Answer

In Worklayer, pull Jira data by asking AI in chat to fetch specific information (sprint status, open bugs, issue details). AI queries Jira via MCP and returns formatted data without manual CSV exports.

Step-by-Step Instructions

Step 1: Verify Jira is Connected

Check that Jira MCP is connected and active.

How to verify:

Go to Settings → MCP Manager
Look for Jira connector with green "Connected" status
If not connected, see "How to connect Jira to Worklayer"

Step 2: Ask AI to Pull Data

In chat, ask AI to fetch specific data from Jira.

Example queries:

Pull all open bugs from Jira and show them in a table.

Get Sprint 12 data from Jira and summarize completion rate.

Pull issues created in the last 7 days from project WORK.

Step 3: Specify Filters (Optional)

Add filters to narrow results: project, status, priority, assignee, or date range.

Example with filters:

Pull P1 bugs from Jira project WORK that are unassigned.

Step 4: Use Data in Workflows

Use pulled data to generate reports, prioritize work, or update stakeholders.

Example:

Pull Sprint 12 data from Jira and create a stakeholder update using @Templates/Work/stakeholder-update-template.md.

Step 5: Save Output (if needed)

Save generated reports to Outcomes/Reports/ for future reference.

Example: End-to-End Workflow

Let's pull sprint data and create a stakeholder update.

Step 1: Verify Jira connection:

Settings → MCP Manager
Jira status: ✓ Connected to worklayer.atlassian.net

Step 2: Pull sprint data:

Pull completed issues from Jira for Sprint 12 (March 15-22) and show:
- Total issues: completed vs planned
- Key deliverables (issue summaries)
- Issues rolled over to next sprint

Step 3: AI returns formatted data:

## Sprint 12 Summary (March 15-22, 2026)

**Completion:** 23/28 issues (82%)

**Completed Issues:**
- WORK-45: Authentication flow with OAuth
- WORK-46: Email verification step
- WORK-50: Onboarding checklist UI
- WORK-51: Progress tracking for onboarding
- WORK-60: Jira MCP integration setup
... (18 more)

**Rolled Over (5 issues):**
- WORK-70: Visual mode performance optimization (blocked by design)
- WORK-71: Skill builder validation (blocked by design)
- WORK-80: File search indexing (carry-over, 50% complete)
- WORK-81: Excel file preview (carry-over, 30% complete)
- WORK-82: PDF export feature (carry-over, not started)

Step 4: Generate stakeholder update using pulled data:

Use the Sprint 12 data above and @Templates/Work/stakeholder-update-template.md to create a stakeholder update for leadership.

Step 5: AI generates update:

# Sprint 12 Update (March 15-22, 2026)

## Progress
- **Completion rate**: 82% (23/28 issues)
- **Key deliverables**:
  - Authentication flow shipped (enables secure login)
  - Onboarding checklist completed (improves Day-1 activation)
  - Jira MCP integration live (pulls live sprint data)

## Metrics
- Day-1 activation: 12% (baseline: 0%, target: 50%)
- Week-1 retention: Not yet measurable (need 7 days of data)

## Risks
- 5 issues rolled to Sprint 13 (2 blocked by design, 3 carry-over)
- Visual mode performance regression needs investigation

## Next Sprint
- Fix visual mode crashes (P1)
- Conduct 5 user feedback sessions
- Ship Skills Builder UI

Save to /Outcomes/Reports/sprint-12-update.md

Time: 2 minutes to pull data + 3 minutes to generate report = 5 minutes total

Tips & Best Practices

Use project keys: Reference Jira projects by key (WORK, BUG) instead of full names for more reliable queries.
Specify date ranges: When pulling data, specify dates (last 7 days, Sprint 12, March 15-22) to avoid pulling too much data.
Pull data before generating reports: Don't generate stakeholder updates from memory. Pull fresh Jira data first, then generate the report.
Save frequently-used queries: If you pull the same data every week (sprint summaries, open P1 bugs), create a skill to automate it.
Combine with context files: Reference @Context/Company/goals-and-okrs.md when using Jira data to show progress against goals, not just completed tasks.

Common Mistakes to Avoid

Pulling too much data: Don't ask for "all issues from Jira" without filters. Specify project, date range, or status to avoid overwhelming results.
Assuming data is current: Jira data is pulled when you ask for it. If you ask in the morning and use the data at night, refresh the query to get updated data.
Not verifying connection first: If Jira MCP is disconnected and you try to pull data, AI will tell you the connection failed. Verify connection status before pulling data.