MCP Atlassian

53 forks

245 stars

Free

What is mcp-atlassian

mcp-atlassian is a Model Context Protocol (MCP) server specifically designed for integrating with Atlassian products like Confluence and Jira. Developed by Sooperset, this server facilitates seamless interaction with both Atlassian Cloud and Jira Server/Data Center deployments. By leveraging MCP, it allows AI systems to securely connect and interact with these platforms, enhancing productivity by enabling advanced automation and data retrieval capabilities.

How to Use mcp-atlassian

To get started with mcp-atlassian, you need to follow a few setup steps:

Authentication Setup: Generate authentication tokens for Atlassian Cloud or Server/Data Center. This involves creating API tokens or Personal Access Tokens (PAT) from your Atlassian account profile.
Installation: You can install mcp-atlassian using different methods:
- Using uv: Recommended for direct execution.
- Using PIP: Install via Python's package manager.
- Using Docker: Clone the repository and build a Docker image.
Configuration: Configure the server by setting necessary environment variables based on the services you wish to integrate. For example, for Confluence Cloud, you need to set CONFLUENCE_URL, CONFLUENCE_USERNAME, and CONFLUENCE_API_TOKEN.
IDE Integration: Integrate with development environments like Cursor IDE by configuring connection settings for accessing MCP tools.

Key Features of mcp-atlassian

Wide Compatibility: Supports both Confluence and Jira on Cloud as well as Server/Data Center platforms.
Flexible Installation Options: Choose from uv, PIP, or Docker for installation based on your preference and existing setup.
Comprehensive Toolset: Access a wide range of tools for both Confluence and Jira, such as searching content, managing pages, handling issues, and more.
Secure and Controlled Access: Utilizes API tokens and personal access tokens for secure and authenticated interactions with Atlassian services.
Real-Time Information: Provides AI systems with the capability to access and process real-time data from Confluence spaces and Jira projects.
Customizable Configuration: Offers a variety of configuration options to tailor the integration to specific organizational needs.
Enhanced Development Workflow: Integrate with IDEs to streamline workflows and improve productivity with MCP-enabled tools.

mcp-atlassian is an ideal solution for organizations looking to enhance their Atlassian toolset with AI-driven capabilities, ensuring efficient and secure management of projects and documentation.

Model Context Protocol (MCP) server for Atlassian products (Confluence and Jira). This integration supports both Atlassian Cloud and Jira Server/Data Center deployments.

Feature Demo

Jira Demo Confluence Demo Confluence Demo

Compatibility

Setup Guide

1. Authentication Setup

First, generate the necessary authentication tokens:

For Atlassian Cloud

Go to
Click Create API token, name it
Copy the token immediately

For Server/Data Center

Go to your profile (avatar) → Profile → Personal Access Tokens
Click Create token, name it, set expiry
Copy the token immediately

2. Installation

Choose one of these installation methods:

Using uv (recommended)

# Install uv on macOS
brew install uv
# Run directly with uvx
uvx mcp-atlassian

Using PIP

pip install mcp-atlassian

Using Docker

git clone 
cd mcp-atlassian
docker build -t mcp/atlassian .

3. Configuration

The integration supports using either Confluence, Jira, or both services. You only need to configure the service(s) you want to use.

Configuration Variables

Note: For all configuration methods, include only the environment variables needed for your services:

For Confluence Cloud: Include CONFLUENCE_URL, CONFLUENCE_USERNAME, and CONFLUENCE_API_TOKEN
For Confluence Server/Data Center: Include CONFLUENCE_URL and CONFLUENCE_PERSONAL_TOKEN
For Jira Cloud: Include JIRA_URL, JIRA_USERNAME, and JIRA_API_TOKEN
For Jira Server/Data Center: Include JIRA_URL and JIRA_PERSONAL_TOKEN
For SSE transport: Add --transport sse and --port arguments View all configuration options | Setting | Environment Variable | CLI Argument | Cloud | Server/DC | | Confluence | | URL | CONFLUENCE_URL | --confluence-url | O | O | | Email | CONFLUENCE_USERNAME | --confluence-username | O | X | | API Token | CONFLUENCE_API_TOKEN | --confluence-token | O | X | | PAT | CONFLUENCE_PERSONAL_TOKEN | --confluence-personal-token | X | O | | Jira | | URL | JIRA_URL | --jira-url | O | O | | Email | JIRA_USERNAME | --jira-username | O | X | | API Token | JIRA_API_TOKEN | --jira-token | O | X | | PAT | JIRA_PERSONAL_TOKEN | --jira-personal-token | X | O | | Common | | SSL Verify | *_SSL_VERIFY | --[no-]*-ssl-verify | X | Optional | | Transport | - | --transport stdio\|sse | Optional | Optional | | Port | - | --port INTEGER | Required for SSE | Required for SSE |

Quick Start Examples

# For Cloud (stdio transport)
uvx mcp-atlassian \
 --confluence-url= \
 --confluence-username=email \
 --confluence-token=token \
 --jira-url= \
 --jira-username=email \
 --jira-token=token
# For Server/DC (SSE transport)
uvx mcp-atlassian \
 --confluence-url= \
 --confluence-personal-token=token \
 --jira-url= \
 --jira-personal-token=token \
 --transport sse \
 --port 8000

4. IDE Integration

Cursor IDE Setup

Open Cursor Settings
Navigate to Features > MCP Servers
Click Add new MCP server

For stdio transport, enter the configuration:

name: mcp-atlassian
type: command
command: uvx mcp-atlassian --confluence-url= --confluence-username=email --confluence-token=token --jira-url= --jira-username=email --jira-token=token

Image

For SSE transport: First, start the MCP server in a terminal:

uvx mcp-atlassian ... --transport sse --port 8000

Then configure Cursor to connect to it:

name: mcp-atlassian
type: sse
Server URL:

Note: The SSE server must be running before you can connect Cursor to it. Image 4. Switch to Agent mode in the Composer to use MCP tools image

Claude Desktop Setup

Using uvx

 "mcpServers": {
 "mcp-atlassian": {
 "command": "uvx",
 "args": ["mcp-atlassian"],
 "env": {
 "CONFLUENCE_URL": "
 "CONFLUENCE_USERNAME": "your.email@domain.com",
 "CONFLUENCE_API_TOKEN": "your_api_token",
 "JIRA_URL": "
 "JIRA_USERNAME": "your.email@domain.com",
 "JIRA_API_TOKEN": "your_api_token"

For Confluence/Jira Server/Data Center:

 "mcpServers": {
 "mcp-atlassian": {
 "command": "uvx",
 "args": ["mcp-atlassian"],
 "env": {
 "CONFLUENCE_URL": "
 "CONFLUENCE_PERSONAL_TOKEN": "your_personal_access_token",
 "JIRA_URL": "
 "JIRA_PERSONAL_TOKEN": "your_personal_access_token"

Using pip

 "mcpServers": {
 "mcp-atlassian": {
 "command": "python",
 "args": ["-m", "mcp-atlassian"],
 "env": {
 "CONFLUENCE_URL": "
 "CONFLUENCE_USERNAME": "your.email@domain.com",
 "CONFLUENCE_API_TOKEN": "your_api_token",
 "JIRA_URL": "
 "JIRA_USERNAME": "your.email@domain.com",
 "JIRA_API_TOKEN": "your_api_token"

Using docker There are two ways to configure the Docker environment:

Using environment variables directly in the config:

 "mcpServers": {
 "mcp-atlassian": {
 "command": "docker",
 "args": ["run", "--rm", "-i", "mcp/atlassian"],
 "env": {
 "CONFLUENCE_URL": "
 "CONFLUENCE_USERNAME": "your.email@domain.com",
 "CONFLUENCE_API_TOKEN": "your_api_token",
 "JIRA_URL": "
 "JIRA_USERNAME": "your.email@domain.com",
 "JIRA_API_TOKEN": "your_api_token"

Using an environment file:

 "mcpServers": {
 "mcp-atlassian": {
 "command": "docker",
 "args": [
 "run",
 "--rm",
 "-i",
 "--env-file",
 "/path/to/your/.env",
 "mcp/atlassian"

The .env file should contain:

# Confluence Cloud
CONFLUENCE_URL= # Your Confluence cloud URL
CONFLUENCE_USERNAME=your.email@domain.com # Your Atlassian account email
CONFLUENCE_API_TOKEN=your_api_token # API token for Confluence
# Confluence Server/Data Center (alternative to CONFLUENCE_USERNAME and CONFLUENCE_API_TOKEN)
# CONFLUENCE_URL= # Your Confluence Server/Data Center URL
# CONFLUENCE_PERSONAL_TOKEN=your_personal_access_token # Personal Access Token for Confluence Server/Data Center
# CONFLUENCE_SSL_VERIFY=true # Set to 'false' for self-signed certificates
# Jira Cloud
JIRA_URL= # Your Jira cloud URL
JIRA_USERNAME=your.email@domain.com # Your Atlassian account email
JIRA_API_TOKEN=your_api_token # API token for Jira Cloud
# Jira Server/Data Center (alternative to JIRA_USERNAME and JIRA_API_TOKEN)
# JIRA_URL= # Your Jira Server/Data Center URL
# JIRA_PERSONAL_TOKEN=your_personal_access_token # Personal Access Token for Jira Server/Data Center
# JIRA_SSL_VERIFY=true # Set to 'false' for self-signed certificates

Resources

Note: The MCP server filters resources to only show Confluence spaces and Jira projects that the user is actively interacting with, based on their contributions and assignments.

confluence://{space_key}: Access Confluence spaces
jira://{project_key}: Access Jira projects

Available Tools

Development & Debugging

Local Development Setup

If you've cloned the repository and want to run a local version:

 "mcpServers": {
 "mcp-atlassian": {
 "command": "uv",
 "args": [
 "--directory", "/path/to/your/mcp-atlassian",
 "run", "mcp-atlassian",
 "--confluence-url=
 "--confluence-username=your.email@domain.com",
 "--confluence-token=your_api_token",
 "--jira-url=
 "--jira-username=your.email@domain.com",
 "--jira-token=your_api_token"

Debugging Tools

MCP Inspector:

# For standard installation
npx @modelcontextprotocol/inspector uvx mcp-atlassian
# For development installation
cd path/to/mcp-atlassian
npx @modelcontextprotocol/inspector uv run mcp-atlassian

View logs:

tail -n 20 -f ~/Library/Logs/Claude/mcp*.log

Security

Never share API tokens
Keep .env files secure and private
See SECURITY.md for best practices

License

Licensed under MIT - see LICENSE file. This is not an official Atlassian product.

How to Use

To use the mcp-atlassian, follow these steps:

Visit https://github.com/sooperset/mcp-atlassianhttps://github.com/sooper...
Follow the setup instructions to create an account (if required)
Connect the MCP server to your Claude Desktop application
Start using mcp-atlassian capabilities within your Claude conversations

Additional Information

Created

March 12, 2025

Company

sooperset

Related MCP Servers

Start building your own MCP Server

Interested in creating your own MCP Server? Check out the official documentation and resources.

Learn More