MCP JIRA Server
About
MCP (Model Context Protocol) server for JIRA integration
Explore
- Rich Markdown Support: Convert markdown descriptions to properly formatted ADF with support for:
- Headers, paragraphs, and text formatting (bold, italic, inline code)
- Fenced code blocks with syntax highlighting
- Bullet and numbered lists
- Tables and complex formatting elements
- Flexible Field Management:
- Create and update JIRA issues with standard fields: project, summary, description, issue type.
- Robust assignee handling: Provide an email address, and the server resolves it to the correct JIRA accountId for reliable assignment.
- additional_fields parameter supports labels, priority, due dates, and other custom fields.
- Graceful degradation for unavailable fields across different JIRA configurations.
- Multi-Site Configuration: Support for multiple JIRA instances with site aliases, configurable in config.yaml.
- Comprehensive Error Handling: Detailed error messages and logging.
- Transport Flexibility: Support for both stdio and SSE transport modes.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
MCP JIRA ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
- Python 3.11 or later (< 3.13)
- Operating Systems: Linux, macOS, Windows
- Network access to JIRA instance(s)
- Valid JIRA API token(s)
uv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
uv pip install -e .
The server requires a config.yaml file to connect to your JIRA instance(s). The server will attempt to load this file from the following locations, in order of precedence:
1. The path specified by the --config command-line argument.
2. The path specified by the MCP_JIRA_CONFIG_PATH environment variable.
3. The default OS-specific user configuration directory:
Linux: ~/.config/mcp_jira/config.yaml
macOS: ~/Library/Application Support/mcp_jira/config.yaml
* Windows: %APPDATA%\MCPJira\mcp_jira\config.yaml (Note: %APPDATA% usually resolves to C:\Users\<username>\AppData\Roaming)
If the configuration file is not found at any of these locations, the server will automatically create the necessary directory (if it doesn't exist) and a template config.yaml file at the default OS-specific path. You will then need to edit this template with your actual JIRA site details.
Example of a filled-in config.yaml:
name: "My Company JIRA Integration"
log_level: "INFO" # Supported levels: DEBUG, INFO, WARNING, ERROR, CRITICAL
default_site_alias: "prod_jira"
sites:
prod_jira:
url: "https://mycompany.atlassian.net"
email: "[email protected]"
api_token: "abc123xyz789efg_your_token_here_jkl"
cloud: true
dev_jira:
url: "https://dev-mycompany.atlassian.net"
email: "[email protected]"
api_token: "another_token_for_dev_environment"
cloud: true
This project includes a web-based configuration editor built with Streamlit to easily manage your config.yaml file.
1. Ensure all project dependencies, including Streamlit, are installed:
uv pip install -e .
2. From the root of the project directory, run:
streamlit run mcp_jira/ui/app.py
Or, if
mcp_jira is installed in your environment and your PYTHONPATH is set up: PYTHONPATH=. streamlit run mcp_jira/ui/app.py
3. Open the URL provided by Streamlit in your web browser.
mcp_jira-server --config /path/to/config.yaml
This server exposes the following tools for interacting with JIRA:
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp jira server": {
"mcp_jira": {
"command": "uv",
"args": [
"venv"
]
}
}
}
}McpServers
{
"mcp_jira": {
"command": "uv",
"args": [
"venv"
]
}
}A Model Context Protocol (MCP) server that provides seamless JIRA integration for AI tools. Create and manage JIRA issues with rich markdown formatting, automatic conversion to Atlassian Document Format (ADF), and flexible field management.
Overview
This MCP server enables AI assistants to interact directly with JIRA instances through the JIRA REST API v3. It handles the complexity of markdown-to-ADF conversion, field mapping, and multi-site configuration, allowing AI tools to create well-formatted JIRA issues with minimal setup.
Key architectural components:
- MCP Server: FastMCP-based server with stdio/SSE transport support
- JIRA Client: Direct REST API integration with authentication handling
- Markdown Converter: Converts markdown to Atlassian Document Format (ADF)
- Configuration System: Multi-site JIRA configuration with flexible site selection
- Field Management: Support for both standard and custom JIRA fields
Features
- Rich Markdown Support: Convert markdown descriptions to properly formatted ADF with support for:
- Headers, paragraphs, and text formatting (bold, italic, inline code)
- Fenced code blocks with syntax highlighting
- Bullet and numbered lists
- Tables and complex formatting elements
- Flexible Field Management:
- Create and update JIRA issues with standard fields: project, summary, description, issue type.
- Robust assignee handling: Provide an email address, and the server resolves it to the correct JIRA accountId for reliable assignment.
- additional_fields parameter supports labels, priority, due dates, and other custom fields.
- Graceful degradation for unavailable fields across different JIRA configurations.
- Multi-Site Configuration: Support for multiple JIRA instances with site aliases, configurable in config.yaml.
- Comprehensive Error Handling: Detailed error messages and logging.
- Transport Flexibility: Support for both stdio and SSE transport modes.
Installation
From Source
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
