A RetroSearch Logo

Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Search Query:

Showing content from https://github.com/tom28881/mcp-jira-server below:

tom28881/mcp-jira-server: Comprehensive MCP server for Jira integration with Claude Code

MCP Jira Server fo Claude Code

A comprehensive Model Context Protocol (MCP) server for Jira integration with Claude Code. This server provides complete Jira functionality including issue management, sprint operations, comments, attachments, and batch processing.

⚠️ Security Note: Never commit your API tokens! All credentials should be in .env files or environment variables.

📋 Issue Management (12 tools) 💬 Comments & History (3 tools) 🏃 Sprint & Agile Management (4 tools)
  1. Clone the repository:
git clone https://github.com/tom28881/JIRA_MCP.git
cd JIRA_MCP
  1. Install dependencies:
  1. Build the project:
  1. Create a .env file from the example:
  1. Configure your Jira credentials in .env:
JIRA_HOST=https://your-company.atlassian.net
JIRA_EMAIL=your-email@company.com
JIRA_API_TOKEN=your-api-token
JIRA_DEFAULT_PROJECT=PROJ
  1. Log in to Atlassian account settings
  2. Click "Create API token"
  3. Give it a name (e.g., "MCP Server")
  4. Copy the token and add it to your .env file
Claude Code Configuration

To use this MCP server with Claude Code, you need to configure it in your MCP settings.

Option 1: Using Environment Variables

Set up the server with environment variables:

# Export environment variables
export JIRA_HOST="https://your-company.atlassian.net"
export JIRA_EMAIL="your-email@company.com"
export JIRA_API_TOKEN="your-api-token"
export JIRA_DEFAULT_PROJECT="PROJ"

# Run Claude Code with the MCP server
claude --mcp "node /absolute/path/to/mcp-jira-server/dist/index.js"
Option 2: Using .env File

Create a .env file in the server directory and run:

cd /path/to/mcp-jira-server
claude --mcp "node dist/index.js"
# or use the convenient run script:
claude --mcp "./run.sh"
Option 3: Add to Claude Code Settings

Add the server to your Claude Code settings file (~/.claude/settings.json):

{
  "mcpServers": [
    {
      "name": "jira",
      "command": "node",
      "args": ["/absolute/path/to/mcp-jira-server/dist/index.js"],
      "env": {
        "JIRA_HOST": "https://your-company.atlassian.net",
        "JIRA_EMAIL": "your-email@company.com",
        "JIRA_API_TOKEN": "your-api-token",
        "JIRA_DEFAULT_PROJECT": "PROJ"
      }
    }
  ]
}
Create a new bug in project PROJ with high priority about login issues

Create a story "Implement user authentication" with 5 story points and assign it to john@example.com
Setting Dates and Time Estimates 
Create task "Database backup" with dueDate "next week" and originalEstimate "4h"

Update PROJ-123 with startDate "tomorrow" and dueDate "+14d"

Create issue "Quarterly review" with dueDate "31.3.2025" and originalEstimate "2 days"
Creating Epics with Subtasks 
Create an epic "Database Migration" in project PROJ with subtasks "Backup current data" and "Migrate schema"

Create a subtask "Review code" for parent issue PROJ-123

Create issue type "Úkol" in project PROJ

Create task for epic PPC-48 with summary "Database backup"

Find all open bugs assigned to me

Search for issues in project PROJ with label "urgent" that are not done

Search issues due before "next week" in project PROJ

Find issues created after "2024-12-01" and updated after "yesterday"

Search for overdue issues: dueBefore "today" and status != "Done"

Update PROJ-123 to add story points 8

Transition PROJ-456 to "In Progress"

Link PROJ-123 to PROJ-456 as "blocks"

Note: Epic-Story relationships use the epicLink field, not regular issue links:

Update PROJ-456 with epicLink "PROJ-100"  # Links story to epic

Generate a standup report for john@example.com

Help me plan the sprint for project PROJ

Create release notes for version 2.0 in project PROJ

The server can work with any Jira configuration:

Option 1: Auto-Detection (Recommended)

Leave custom field IDs unset in .env and the server will automatically detect them based on field names.

Option 2: Manual Configuration

If auto-detection doesn't work, configure custom field IDs in your .env:

JIRA_FIELD_STORY_POINTS=customfield_10001
JIRA_FIELD_ACCEPTANCE_CRITERIA=customfield_10002
JIRA_FIELD_EPIC_LINK=customfield_10003

Use the diagnose-fields tool to find the correct field IDs for your Jira instance:

diagnose-fields project:"PROJ" issueType:"Story"

Enable automatic test ticket creation for stories:

AUTO_CREATE_TEST_TICKETS=true
Running in Development Mode 📅 Date and Time Management

The server automatically retries failed requests with exponential backoff (up to 3 attempts).

Enable debug logging to see detailed information:

DEBUG=* claude --mcp "./run.sh"
# or specific to jira-mcp:
DEBUG=jira-mcp claude --mcp "./run.sh"

The server tests the connection on startup and provides clear error messages if authentication fails.

📄 Atlassian Document Format

Automatically converts plain text and markdown to Jira's ADF format for rich text fields.

Working with Different Jira Configurations

This MCP server is designed to work with any Jira instance regardless of:

Best Practices:

  1. Use get-fields to see available issue types in your language
  2. Use diagnose-fields to find custom field IDs
  3. Create issues using the exact issue type names from your Jira

  1. Authentication Failed

  2. Project Not Found

  3. Custom Fields Not Working

  4. Link Type Not Found

  5. Epic-Story Linking Issues

Set the DEBUG environment variable for verbose logging:

DEBUG=* claude --mcp "./run.sh"
# or
DEBUG=jira-mcp claude --mcp "./run.sh"

Logs are output to stderr and include:

See CONTRIBUTING.md for development guidelines.

MIT License - see LICENSE file for details

For issues and feature requests, please use the GitHub issue tracker.

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4