MCP Jira Integration

A simple Model Context Protocol (MCP) server for Jira that allows LLMs to act as project managers and personal assistants for teams using Jira. Built on the Jira REST API v3.

Features

Core MCP Tools

• create_issue - Create new Jira issues with proper formatting and ADF descriptions
• search_issues - Search issues using JQL with smart formatting and pagination
• get_sprint_status - Get comprehensive sprint progress reports with metrics
• get_team_workload - Analyze team member workloads and capacity
• generate_standup_report - Generate daily standup reports automatically

Project Management Capabilities

• Multi-Project Support: Work with multiple projects by specifying project keys dynamically
• Sprint progress tracking with visual indicators
• Team workload analysis and capacity planning
• Automated daily standup report generation
• Issue creation with proper prioritization
• Smart search and filtering of issues

Reliability

• Automatic retry with exponential backoff on rate limits (429) and transient errors (503)
• Pagination for large result sets
• Timezone-aware date handling
• Graceful handling of custom Jira statuses and issue types

Requirements

• Python 3.8 or higher
• Jira Cloud account with API token
• MCP-compatible client (like Claude Desktop)

Quick Setup

1. Clone and install:

git clone https://github.com/your-org/mcp-jira.git
cd mcp-jira
python3 -m venv .venv
source .venv/bin/activate
pip install -e .

2. Configure Jira credentials:

cp .env.example .env
# Edit .env with your values

JIRA_URL=https://your-domain.atlassian.net
[email protected]
JIRA_API_TOKEN=your_api_token
PROJECT_KEY=PROJ
DEFAULT_BOARD_ID=123

3. Test the server:

.venv/bin/python -m mcp_jira

You should see Initializing MCP Jira server... in the output. Press Ctrl+C to stop.

Usage Examples

Creating Issues

“Create a high priority bug for the login system not working properly”

• Auto-assigns proper issue type, priority, and formatting

Sprint Management

“What’s our current sprint status?”

• Gets comprehensive progress report with metrics and visual indicators

Team Management

“Show me the team workload for john.doe, jane.smith, mike.wilson”

• Analyzes capacity and provides workload distribution

Daily Standups

“Generate today’s standup report”

• Creates formatted report with completed, in-progress, and blocked items

MCP Integration

With Claude Desktop

The config file is located at:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

Add the following entry, replacing /path/to/mcp-jira with the absolute path where you cloned the repo:

{
  "mcpServers": {
    "mcp-jira": {
      "command": "/path/to/mcp-jira/.venv/bin/python",
      "args": ["-m", "mcp_jira"]
    }
  }
}