Skip to content

Installation

MCP Atlassian can be installed using several methods. Choose the one that best fits your workflow.

Note

Package vs command name — This fork is published as mcp-atlassian-ry on PyPI, but the CLI command (inherited from upstream) is mcp-atlassian. Use --from to be explicit about which package you're running: uvx --from mcp-atlassian-ry mcp-atlassian

The simplest way to run MCP Atlassian without permanent installation using uvx:

# Run directly (downloads on first use, cached for subsequent runs)
uvx --from mcp-atlassian-ry mcp-atlassian --help

# Run with a specific Python version if needed
uvx --python=3.12 --from mcp-atlassian-ry mcp-atlassian --help

IDE Configuration with uvx

Edit your config file: - macOS: ~/Library/Application Support/Claude/claude_desktop_config.json - Windows: %APPDATA%\Claude\claude_desktop_config.json - Linux: ~/.config/Claude/claude_desktop_config.json

```json
{
  "mcpServers": {
    "mcp-atlassian-ry": {
      "command": "uvx",
      "args": [
        "--from", "mcp-atlassian-ry",
        "mcp-atlassian"
      ],
      "env": {
        "CONFLUENCE_URL": "https://your-company.atlassian.net/wiki",
        "CONFLUENCE_USERNAME": "your.email@company.com",
        "CONFLUENCE_API_TOKEN": "your_confluence_api_token",
        "JIRA_URL": "https://your-company.atlassian.net",
        "JIRA_USERNAME": "your.email@company.com",
        "JIRA_API_TOKEN": "your_jira_api_token"
      }
    }
  }
}
```

Open Settings → MCP → + Add new global MCP server, then use the same JSON configuration.

Docker

Docker provides an isolated environment and is recommended for production deployments or when you need specific version control.

# Pull the latest image
docker pull ghcr.io/sooperset/mcp-atlassian:latest

# Run with environment variables
docker run --rm -i \
  -e JIRA_URL=https://your-company.atlassian.net \
  -e JIRA_USERNAME=your.email@company.com \
  -e JIRA_API_TOKEN=your_api_token \
  ghcr.io/sooperset/mcp-atlassian:latest

IDE Configuration with Docker

{
  "mcpServers": {
    "mcp-atlassian": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "CONFLUENCE_URL",
        "-e", "CONFLUENCE_USERNAME",
        "-e", "CONFLUENCE_API_TOKEN",
        "-e", "JIRA_URL",
        "-e", "JIRA_USERNAME",
        "-e", "JIRA_API_TOKEN",
        "ghcr.io/sooperset/mcp-atlassian:latest"
      ],
      "env": {
        "CONFLUENCE_URL": "https://your-company.atlassian.net/wiki",
        "CONFLUENCE_USERNAME": "your.email@company.com",
        "CONFLUENCE_API_TOKEN": "your_confluence_api_token",
        "JIRA_URL": "https://your-company.atlassian.net",
        "JIRA_USERNAME": "your.email@company.com",
        "JIRA_API_TOKEN": "your_jira_api_token"
      }
    }
  }
}

See Configuration for more Docker options including environment files.

pip

Install directly with pip for development or when you need the package in your Python environment:

pip install mcp-atlassian-ry

# Run the server
mcp-atlassian --help

uv

If you're using uv for package management:

# Add to your project
uv add mcp-atlassian-ry

# Run
uv run mcp-atlassian --help

From Source

For development or contributing:

git clone https://github.com/sriluxman/mcp-atlassian-ry-xr.git
cd mcp-atlassian
uv sync --frozen --all-extras --dev
uv run mcp-atlassian --help

See CONTRIBUTING.md for development setup details.