atlassian-browser-mcp
rowser-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.
atlassian-browser-mcp
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
- On first use (or when the session expires), Playwright opens a real Chromium window for manual SSO/MFA
- After login, cookies are saved to a Playwright storage-state file
- All subsequent MCP tool calls use those cookies via a custom
requests.Sessionsubclass - 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
Verwandte Server
Scout Monitoring MCP
SponsorPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
SponsorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Zeek-MCP
Integrates Zeek network analysis with conversational AI clients. Requires an external Zeek installation.
MCP OAuth Sample
A sample MCP OAuth server implementation using Next.js, providing OAuth 2.1 authentication with Google and PostgreSQL.
Remote MCP Server (Authless)
An authentication-free, remote MCP server deployable on Cloudflare Workers. Customize tools directly in the source code and deploy via Cloudflare or locally.
GitHub Trending
Access GitHub's trending repositories and developers.
Snak
An agent engine for creating powerful and secure AI Agents powered by Starknet.
Docker Hub README MCP Server
Search for Docker images and retrieve their READMEs and metadata from Docker Hub.
Unimus MCP Server
A read-only server for the Unimus network configuration management system.
Kubernetes Automated Installation
An agent for automatically installing Kubernetes in a Rocky Linux environment using MCP.
Domscribe
Build-time DOM-to-source mapping for coding agents
Remote MCP Server (Authless)
An example of a remote MCP server deployable on Cloudflare Workers, without authentication.