Agent Skills

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.

Install

Install and configure the MCP from https://github.com/GeiserX/atlassian-browser-mcp now. Follow the repository's installation instructions, ask me for anything you can't complete yourself, and verify its tools load.
README

atlassian-browser-mcp

MCP server that wraps the upstream mcp-atlassian toolset with browser-cookie authentication via Playwright, for Atlassian Server/Data Center instances behind corporate SSO (Okta, SAML, etc.) where API tokens are not available. It runs locally over stdio: you log in once with the bundled CLI, and the server reuses the cookies.

Features

  • Every mcp-atlassian Jira and Confluence tool, authenticated with your SSO browser session instead of an API token.
  • One login per service with the CLI; the server itself never opens a browser, so it never hangs waiting for one.
  • Seeds the automation profile from your real Chrome profile, so the first login is often one click.
  • On macOS, reuses a live session from an installed Chromium-family browser (Arc, Brave, Edge, Chrome and others) without opening a window.
  • Separate cookie jars for Jira and Confluence.
  • A command-line front-end (atlassian-cli) for scripts and agents: get and search issues and pages.
  • Falls back to token auth with ATLASSIAN_BROWSER_AUTH_ENABLED=false.

Quick start

git clone https://github.com/GeiserX/atlassian-browser-mcp.git && cd atlassian-browser-mcp
uv venv --python 3.11 .venv-atlassian-browser && uv pip install --python .venv-atlassian-browser/bin/python -e .
JIRA_URL=https://jira.example.com CONFLUENCE_URL=https://confluence.example.com ./atlassian-cli login jira   # once per service

Then point your MCP client at the launcher:

{
  "mcpServers": {
    "atlassian": {
      "command": "/path/to/atlassian-browser-mcp/run-atlassian-browser-mcp.sh",
      "env": {
        "JIRA_URL": "https://jira.example.com",
        "CONFLUENCE_URL": "https://confluence.example.com"
      }
    }
  }
}

Needs Python 3.11+, uv, Google Chrome and a display for the login. The server only reads the saved cookies; when they expire it returns an AuthRequiredError asking you to run the login again. Seeding from Chrome and every setting are in Getting started.

Documentation

  • Getting started: requirements, install, the first login, seeding from Chrome, the MCP client config
  • Configuration: every environment variable and its default
  • Usage: the MCP tools and the CLI commands
  • How it works: why login and serving are separate processes, and the files
  • Troubleshooting: symptoms, causes, fixes, and what to put in a bug report

License

GPL-3.0-or-later

Search skills and MCP servers

Search across 31,816 skills and MCPs