Atlassian Data Center MCP Server

@b1ff

代码仓库

基本信息

分类

版本控制

许可证

MIT

传输方式

stdio

作者

b1ff

关于 Atlassian Data Center MCP Server

MCP servers for the Atlassian products (Bitbucket, Confluence, JIRA) of the Data Center version

Atlassian Data Center MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "atlassian-dc-mcp": {
      "command": "npx",
      "args": [
        "@atlassian-dc-mcp/jira",
        "setup"
      ]
    }
  }
}

Atlassian Data Center MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。

概览

What is Atlassian Data Center MCP?

Atlassian Data Center MCP is a community-maintained Model Context Protocol integration for Atlassian Data Center products—Jira, Confluence, and Bitbucket. It allows AI assistants to interact with self-hosted Atlassian instances via MCP servers.

How to use Atlassian Data Center MCP?

Run the interactive setup subcommand for each product (e.g., npx @atlassian-dc-mcp/jira setup) to store credentials securely. Once configured, add the servers to your MCP host (Claude Desktop, Claude Code) using npx commands and environment variables like JIRA_HOST and JIRA_API_TOKEN. You can also use a shared external config file with ATLASSIAN_DC_MCP_CONFIG_FILE.

Key features of Atlassian Data Center MCP

Interactive setup CLI for each product with credential validation.
Non-interactive mode for scripted or CI bootstrap.
Secure token storage: macOS Keychain, Linux home file, Windows user profile.
Multi-source configuration with clear precedence (env, shared file, home file, keychain).
Supports both *_HOST and *_API_BASE_PATH environment variables.
Configurable request timeout via ATLASSIAN_DC_MCP_REQUEST_TIMEOUT_MS.

Use cases of Atlassian Data Center MCP

Enable an AI assistant to query or manage Jira issues in a self-hosted Data Center instance.
Let AI search Confluence pages and spaces from an on‑premises Confluence Data Center.
Integrate Bitbucket repositories and pull requests into AI‑powered workflows.
Share a single set of Atlassian credentials across multiple MCP hosts and tools.

常见问题

How does it authenticate to Atlassian Data Center?

It uses Personal Access Tokens (PAT) generated in each Data Center product. The token is stored securely during the `setup` process or passed via environment variables.

What are the configuration sources and precedence?

The server checks, in order: `process.env` (highest), a shared config file (`ATLASSIAN_DC_MCP_CONFIG_FILE`), the home file (`~/.atlassian-dc-mcp/<product>.env`), and the macOS Keychain (token only). The first non‑empty value wins.

Can I use a single config file for multiple products?

Yes. Set `ATLASSIAN_DC_MCP_CONFIG_FILE` to the absolute path of a dotenv file containing `JIRA_*`, `CONFLUENCE_*`, and `BITBUCKET_*` variables. Each server will read from it.

What is the difference between `_HOST` and `_API_BASE_PATH`?

`*_HOST` expects only domain and port (protocol assumed HTTPS). `*_API_BASE_PATH` accepts the full API base URL including protocol (e.g., `https://your-instance.atlassian.net/rest`). The `/api/latest/` path is added automatically.

What happens if a credential validation fails during non‑interactive setup?

Non‑interactive mode exits with code 1 on the first validation failure, making it suitable as a CI gate. Interactive mode offers retry or save‑anyway prompts.

版本控制分类下的更多 MCP 服务器

Gerrit Review MCP Server

cayirtepeomer

This MCP server provides integration with Gerrit code review system, allowing AI assistants to review code changes and their details through a simple interface.

GitHub MCP Server Extension for Zed

LoamStudios

A GitHub MCP Server extension for Zed

🚀 GitLab MR MCP

kopfrechner

Interact seamlessly with GitLab repositories to manage merge requests and issues. Fetch details, add comments, and streamline your code review process with ease.