atlassian-browser-mcp

atlassian-browser-mcp

Browser-backed MCP wrapper for mcp-atlassian with Playwright SSO auth. Enables AI tools to access Atlassian Server/Data Center instances behind corporate SSO (Okta, SAML, ADFS) where API tokens are not available

Category
访问服务器

README

atlassian-browser-mcp

License: GPL-3.0 Python 3.12+ GitHub stars mcp-atlassian

MCP server that wraps the upstream mcp-atlassian toolset with browser-cookie authentication via Playwright. Designed for Atlassian Server/Data Center instances behind corporate SSO (Okta, SAML, etc.) where API tokens are not available.

How it works

  1. On first use (or when the session expires), Playwright opens a real Chromium window for manual SSO/MFA
  2. After login, cookies are saved to a Playwright storage-state file
  3. All subsequent MCP tool calls use those cookies via a custom requests.Session subclass
  4. If an API response looks like an SSO redirect, the browser reopens automatically

The server monkey-patches JiraClient and ConfluenceClient constructors in mcp-atlassian to inject the browser-backed session, giving full parity with the upstream tool surface (72 tools + 1 atlassian_login helper = 73 total).

Files

File Purpose
atlassian_browser_mcp_full.py Entrypoint. Patches upstream clients, registers atlassian_login tool, runs the MCP server
atlassian_browser_auth.py Shared auth: BrowserCookieSession, interactive_login(), SSO detection
run-atlassian-browser-mcp.sh Launcher: creates venv, installs deps via uv, runs compatibility check, starts server
pyproject.toml Dependency pins

Usage

./run-atlassian-browser-mcp.sh

Or configure as an MCP server in your editor (Cursor, Claude Code, etc.) pointing to the launcher script.

Environment variables

Variable Default Description
JIRA_URL (required) Jira base URL (e.g. https://jira.example.com)
CONFLUENCE_URL (required) Confluence base URL (e.g. https://confluence.example.com)
ATLASSIAN_BROWSER_AUTH_ENABLED true Enable browser auth (set false to fall back to token auth)
ATLASSIAN_BROWSER_PROFILE_DIR ./.atlassian-browser-profile Persistent Chromium profile directory
ATLASSIAN_STORAGE_STATE ./.atlassian-browser-state.json Playwright storage-state file
ATLASSIAN_LOGIN_TIMEOUT_SECONDS 300 Seconds to wait for manual login
ATLASSIAN_USERNAME (none) Optional: prefill username on SSO page
ATLASSIAN_SSO_MARKERS (auto) Comma-separated URL/text markers for SSO redirect detection. Defaults cover Okta, ADFS, Azure AD, PingOne, Google SAML
TOOLSETS all Which upstream toolsets to enable

Requirements

  • Python 3.12+
  • uv (for dependency management)
  • Chromium (installed automatically by Playwright)
  • Network access to your Atlassian instance

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选