atlassian-hub 0.2.0

The Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification. This project enables secure, contextual AI interactions with Atlassian tools while maintaining data privacy and security. Key features include:

MCP Atlassian

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

https://github.com/user-attachments/assets/35303504-14c6-4ae4-913b-7c25ea511c3e

Confluence Demo

https://github.com/user-attachments/assets/7fe9c488-ad0c-4876-9b54-120b666bb785

Quick Start

1. Get Your API Token

Go to https://id.atlassian.com/manage-profile/security/api-tokens and create a token.

For Server/Data Center, use a Personal Access Token instead. See Authentication.

2. Configure Your Client

Add atlassian-hub to your MCP client. Pick the tab matching your setup — the env block is the same across all of them, only the surrounding config format differs.

Claude Desktop / Cursor (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):

{
  "mcpServers": {
    "atlassian-hub": {
      "command": "uvx",
      "args": ["atlassian-hub"],
      "env": {
        "JIRA_URL": "https://your-company.atlassian.net",
        "JIRA_USERNAME": "[e-mail]",
        "JIRA_API_TOKEN": "your_api_token",
        "CONFLUENCE_URL": "https://your-company.atlassian.net/wiki",
        "CONFLUENCE_USERNAME": "[e-mail]",
        "CONFLUENCE_API_TOKEN": "your_api_token"
      }
    }
  }
}

Claude Code (Anthropic CLI)

One-liner via the claude mcp command:

claude mcp add atlassian-hub uvx atlassian-hub \
  -e JIRA_URL=https://your-company.atlassian.net \
  -e JIRA_USERNAME=[e-mail] \
  -e JIRA_API_TOKEN=your_api_token \
  -e CONFLUENCE_URL=https://your-company.atlassian.net/wiki \
  -e CONFLUENCE_USERNAME=[e-mail] \
  -e CONFLUENCE_API_TOKEN=your_api_token

Or edit ~/.claude.json (user-scope) / .mcp.json (project-scope) with the same JSON shape as the Claude Desktop example above.

Codex (OpenAI CLI)

Edit ~/.codex/config.toml:

[mcp_servers.atlassian-hub]
command = "uvx"
args = ["atlassian-hub"]

[mcp_servers.atlassian-hub.env]
JIRA_URL = "https://your-company.atlassian.net"
JIRA_USERNAME = "[e-mail]"
JIRA_API_TOKEN = "your_api_token"
CONFLUENCE_URL = "https://your-company.atlassian.net/wiki"
CONFLUENCE_USERNAME = "[e-mail]"
CONFLUENCE_API_TOKEN = "your_api_token"

GitHub Copilot (VS Code MCP)

Create .vscode/mcp.json in your workspace (or add under "mcp.servers" in VS Code settings):

{
  "servers": {
    "atlassian-hub": {
      "type": "stdio",
      "command": "uvx",
      "args": ["atlassian-hub"],
      "env": {
        "JIRA_URL": "https://your-company.atlassian.net",
        "JIRA_USERNAME": "[e-mail]",
        "JIRA_API_TOKEN": "your_api_token",
        "CONFLUENCE_URL": "https://your-company.atlassian.net/wiki",
        "CONFLUENCE_USERNAME": "[e-mail]",
        "CONFLUENCE_API_TOKEN": "your_api_token"
      }
    }
  }
}

For secrets, prefer ${input:jira_token} placeholders with inputs[].type = "promptString" rather than committing tokens to the file.

opencode

Edit opencode.json (project-scope) or ~/.config/opencode/opencode.json:

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "atlassian-hub": {
      "type": "local",
      "command": ["uvx", "atlassian-hub"],
      "enabled": true,
      "environment": {
        "JIRA_URL": "https://your-company.atlassian.net",
        "JIRA_USERNAME": "[e-mail]",
        "JIRA_API_TOKEN": "your_api_token",
        "CONFLUENCE_URL": "https://your-company.atlassian.net/wiki",
        "CONFLUENCE_USERNAME": "[e-mail]",
        "CONFLUENCE_API_TOKEN": "your_api_token"
      }
    }
  }
}

Server/Data Center users: Use JIRA_PERSONAL_TOKEN instead of JIRA_USERNAME + JIRA_API_TOKEN. See Authentication for details.

3. Start Using

Ask your AI assistant to:

• "Find issues assigned to me in PROJ project"
• "Search Confluence for onboarding docs"
• "Create a bug ticket for the login issue"
• "Update the status of PROJ-123 to Done"

Documentation

Full documentation is available at mcp-atlassian.soomiles.com.

Note: The docs site covers the original mcp-atlassian package. Everything applies equally to atlassian-hub — wherever you see mcp-atlassian in installation or configuration examples, substitute atlassian-hub.

Documentation is also available in llms.txt format, which LLMs can consume easily:

• llms.txt — documentation sitemap
• llms-full.txt — complete documentation

Topic	Description
Installation	uvx, Docker, pip, from source
Authentication	API tokens, PAT, OAuth 2.0
Configuration	IDE setup, environment variables
HTTP Transport	SSE, streamable-http, multi-user
Tools Reference	All Jira & Confluence tools
Troubleshooting	Common issues & debugging

Compatibility

Product	Deployment	Support
Confluence	Cloud	Fully supported
Confluence	Server/Data Center	Supported (v6.0+)
Jira	Cloud	Fully supported
Jira	Server/Data Center	Supported (v8.14+)

Key Tools

Jira	Confluence
jira_search - Search with JQL	confluence_search - Search with CQL
jira_get_issue - Get issue details	confluence_get_page - Get page content
jira_create_issue - Create issues	confluence_create_page - Create pages
jira_update_issue - Update issues	confluence_update_page - Update pages
jira_transition_issue - Change status	confluence_add_comment - Add comments

72 tools across 21 toolsets — by default only the 6 core toolsets (~23 tools) are enabled to keep the AI assistant's context lean. Set TOOLSETS=all to enable everything, or TOOLSETS=default,jira_agile to add specific extras. See Tools Reference for the full list.

Security

Never share API tokens. Keep .env files secure. See SECURITY.md.

Contributing

See CONTRIBUTING.md for development setup, workflow, and the full release & PyPI publish process (versioning via git tags, uv build, uvx uv-publish).

License

MIT - See LICENSE. Not an official Atlassian product.