Atlassian Dc MCP Server
Jira, Confluence, and Bitbucket connectivity for your AI assistant via MCP.
Data last scanned today · Reviewed today
Overview
Atlassian Data Center MCP enables AI models to interface with Jira, Confluence, and Bitbucket. By utilizing an interactive setup subcommand, users can securely configure connections to these platforms, with credentials stored locally using platform-specific security measures like the macOS Keychain or encrypted environment files on Linux.
Our verdict
With a security score of 40/100, this server is currently classified as high risk. Because it is community-maintained and has not yet undergone editorial review or security auditing, users should exercise caution when handling sensitive internal data. It is primarily suitable for users in environments where they can manually verify the code and handle their own authentication risks.
- Zero direct dependencies reduce the supply chain attack surface.
- Integrated credential validation checks connectivity during the setup phase.
- Automated CLI setup supports non-interactive bootstrap for CI environments.
- Not an official product or supported by Atlassian.
- Lacks external editorial review of authentication and read-only implementations.
- No public homepage link available for official project documentation.
Setup
{
"mcpServers": {
"atlassian-dc-mcp": {
"args": [
"-y",
"atlassian-dc-mcp"
],
"command": "npx"
}
}
}Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows), then restart Claude Desktop. Some servers require API keys or tokens as environment variables — check the project's README and add an "env" object if needed.
- No read-only mode — running this grants full read/write access.
- No built-in authentication — anyone with access to this config can invoke every tool it exposes.
Compatibility
| Client | Local | Docker | Remote | Read-only |
|---|---|---|---|---|
| Claude Desktop | ||||
| Cursor | ||||
| VS Code | ||||
| Windsurf | ||||
| ChatGPT |
Frequently asked questions
›How do I securely store my Atlassian API credentials for this MCP server?
Each product package provides a setup subcommand that stores your credentials in the most secure location available on your OS, such as the macOS Keychain or a restricted permission file on Linux and Windows.
›Can I configure the server without using the interactive setup process?
Yes, you can use the non-interactive mode with CLI flags, which is suitable for automated CI or scripted bootstrapping, and will return an exit code of 1 if validation fails.
›What is the order of precedence for configuration values?
The server resolves configuration by checking environment variables first, then an explicit environment file, then the standard home configuration file, and finally the macOS Keychain for stored tokens.
›Does this server require specific environment variables to function?
No, once the setup command has been run, the MCP servers can start successfully without any environment variables as they will use the locally stored configuration.
›Is it possible to override stored credentials for a specific session?
Yes, you can use environment variables like JIRA_TOKEN or CONFLUENCE_TOKEN to override stored configuration because process-level environment variables take the highest priority.
›How can I change the default timeout for Atlassian API requests?
You can override the default 30-second timeout by setting the ATLASSIAN_DC_MCP_REQUEST_TIMEOUT_MS environment variable to your desired duration in milliseconds.
Badge
Maintain this server? Add the live badge to your README.