TamarEngel/jira-github-mcp

A modular and extensible Model Context Protocol (MCP) server for Jira and
GitHub integration, enabling end-to-end automation of developer workflows -
from issue tracking to code changes and pull request management - via AI
agents inside the IDE.
Overview
- **Jira integration**: fetch issues by filters, search via JQL, and transition issues across workflows
- **GitHub integration**: create branches, open and merge PRs
- **Local Git operations**: stage, commit, and push changes locally
- **IDE-native**: works with any MCP-compatible agent (e.g., GitHub Copilot) over stdio
- **End-to-end workflow**: Jira issue → branch → code → commit → PR → merge → Jira status update
Why
Developers constantly context-switch between Jira, GitHub, and their IDE,
breaking focus and slowing down delivery. This project transforms that workflow
into a seamless, IDE-native, conversational experience, allowing developers to
move from Jira issue to merged pull request using natural language and
AI-assisted automation.
Features
- **Retrieve, filter, and search** Jira issues using **fields and JQL**
- **Transition** Jira issues across **workflow statuses**
- **Automate branch creation** as part of the **Jira-driven workflow**
- **Commit and push** changes from the **local Git repository**
- **Create and merge** GitHub **pull requests**
- **MCP resources** providing **workflow guidance** and **current issue context**
Available Tools
| Tool | Description |
|------|-------------|
| jira_get_issue | Retrieve a Jira issue by key (e.g., KAN-1) with configurable fields |
| jira_search_issues | Search Jira using JQL; paginate and filter results |
| jira_get_my_issues | List issues assigned to the current user, optionally filtered by status/type... |
| jira_transition_issue | Move an issue to another status with optional comment |
| create_branch_for_issue | Create a new Git branch (e.g., feature/KAN-15) based on a Jira issue |
| create_pull_request | Create a PR on GitHub from a branch |
| git_commit_and_push | Stage all changes, commit with a message, and push to a branch |
| merge_pull_request | Merge a PR using squash, merge, or rebase; optionally check CI status |
Project Structure
- src/ — Application source code
- server/ — MCP server entry point and tool registration
- config/ — Configuration loading for Jira and GitHub
- providers/ — Jira/GitHub API clients and local Git operations
- tools/ — MCP tool definitions and implementations
- resources/ — MCP resources (workflow guidance, issue context)
- prompts/ — AI-facing prompts used internally by the server to guide agent behavior
- tests/ — Integration and unit tests
- pyproject.toml — Project metadata and dependencies
- uv.lock — Dependency lockfile
Architecture Overview
High-level overview of the system design and main components.
See full architecture documentation: docs/architecture.md
Installation & Setup
Requirements
- Python 3.10+
- Git (available on PATH)
- Jira instance (Cloud or self-hosted) with REST API v3 access
- GitHub repository with token-based API access
1. Clone the Repository
2. Create & Activate a Virtual Environment
Using uv (recommended)
Or with python
3. Install Dependencies
Using uv (recommended):
Or with pip:
The project depends on:
- fastmcp: MCP protocol and server utilities
4. Configure Environment Variables
Create a .env file in the repository root: