Atlassian (browser SSO)
Jira and Confluence behind SSO via your own browser session: every mcp-atlassian tool, no API token
What can you do with Atlassian (browser SSO)?
- Every mcp-atlassian Jira and Confluence tool, authenticated with your SSO browser session instead of an API token, with upstream's own network hardening (SSRF redirect checks, DNS pinning, retries, rate limits, proxy and TLS settings) kept in force.
- One login per service with the CLI; the server itself never opens a browser, so it never hangs waiting for one.
atlassian_auth_statustells an agent which service needs a login before it fails mid-task.- Optional one-time seeding of the automation profile from your real Chrome profile (
ATLASSIAN_SEED_FROM_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. It reads that browser's Keychain key, says so on stderr, and can be turned off.
- Separate cookie jars for Jira and Confluence, holding only that host's cookies, mode 0600. Jira-only or Confluence-only setups work.
- 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.
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
atlassian-browser-mcpclaude mcp add atlassian-browser-sso -e 'JIRA_URL=<JIRA_URL>' -e 'CONFLUENCE_URL=<CONFLUENCE_URL>' -e 'READ_ONLY_MODE=<READ_ONLY_MODE>' -e 'ENABLED_TOOLS=<ENABLED_TOOLS>' -e 'ATLASSIAN_BROWSER_AUTH_ENABLED=<ATLASSIAN_BROWSER_AUTH_ENABLED>' -e 'ATLASSIAN_STORAGE_STATE=<ATLASSIAN_STORAGE_STATE>' -- uvx atlassian-browser-mcp==1.4.1
{
"mcpServers": {
"atlassian-browser-sso": {
"command": "uvx",
"args": [
"atlassian-browser-mcp==1.4.1"
],
"env": {
"JIRA_URL": "<JIRA_URL>",
"CONFLUENCE_URL": "<CONFLUENCE_URL>",
"READ_ONLY_MODE": "<READ_ONLY_MODE>",
"ENABLED_TOOLS": "<ENABLED_TOOLS>",
"ATLASSIAN_BROWSER_AUTH_ENABLED": "<ATLASSIAN_BROWSER_AUTH_ENABLED>",
"ATLASSIAN_STORAGE_STATE": "<ATLASSIAN_STORAGE_STATE>"
}
}
}
}
Environment variables
JIRA_URLBase URL of the Jira Server/Data Center instance (set the one you use; Jira-only and Confluence-only setups work)CONFLUENCE_URLBase URL of the Confluence Server/Data Center instanceREAD_ONLY_MODESet to true to hide every write tool (create, update, delete, transition, upload, restrictions)ENABLED_TOOLSComma-separated allow-list of tool names; unset exposes every toolATLASSIAN_BROWSER_AUTH_ENABLEDSet to false to skip the browser session and use upstream token auth insteadATLASSIAN_STORAGE_STATEPath of the saved browser session (cookie jar) written by atlassian-cli login; defaults to the current directory
Documentation
From the project's README on GitHub, refreshed weekly. Links open on GitHub.
Contents
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, with upstream's own network hardening (SSRF redirect checks, DNS pinning, retries, rate limits, proxy and TLS settings) kept in force.
- One login per service with the CLI; the server itself never opens a browser, so it never hangs waiting for one.
atlassian_auth_statustells an agent which service needs a login before it fails mid-task.- Optional one-time seeding of the automation profile from your real Chrome profile (
ATLASSIAN_SEED_FROM_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. It reads that browser's Keychain key, says so on stderr, and can be turned off.
- Separate cookie jars for Jira and Confluence, holding only that host's cookies, mode 0600. Jira-only or Confluence-only setups work.
- 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
From PyPI, with uv installed:
JIRA_URL=https://jira.example.com uvx --from atlassian-browser-mcp atlassian-cli login jira # once per service, opens your browser
CONFLUENCE_URL=https://confluence.example.com uvx --from atlassian-browser-mcp atlassian-cli login confluence
JIRA_URL=https://jira.example.com CONFLUENCE_URL=https://confluence.example.com uvx atlassian-browser-mcp
From a checkout, with the exact versions in uv.lock:
git clone https://github.com/GeiserX/atlassian-browser-mcp.git && cd atlassian-browser-mcp
UV_PROJECT_ENVIRONMENT=.venv-atlassian-browser uv sync --frozen # installs the versions in uv.lock
JIRA_URL=https://jira.example.com CONFLUENCE_URL=https://confluence.example.com ./atlassian-cli login jira # once per service
Needs Python 3.11+, uv, Google Chrome and a display for the login. The server never opens a browser window. It reads the saved cookies; when they are missing or expired it returns an AuthRequiredError asking you to run the login again, and on macOS it also looks for a live session in your installed browsers in the background, so a retry a few seconds later may already work. Seeding from Chrome and every setting are in Getting started.
Add it to your client
Every client runs the server over stdio. Set only the URL of a service you use. The examples use the PyPI package through uvx; from a checkout, replace uvx atlassian-browser-mcp with /path/to/atlassian-browser-mcp/run-atlassian-browser-mcp.sh.
Claude Code
claude mcp add --transport stdio atlassian \
--env JIRA_URL=https://jira.example.com \
--env CONFLUENCE_URL=https://confluence.example.com \
-- uvx atlassian-browser-mcp
Claude Desktop (claude_desktop_config.json) and Cursor (~/.cursor/mcp.json or .cursor/mcp.json)
{
"mcpServers": {
"atlassian": {
"command": "uvx",
"args": ["atlassian-browser-mcp"],
"env": {
"JIRA_URL": "https://jira.example.com",
"CONFLUENCE_URL": "https://confluence.example.com"
}
}
}
}
VS Code (.vscode/mcp.json)
{
"servers": {
"atlassian": {
"type": "stdio",
"command": "uvx",
"args": ["atlassian-browser-mcp"],
"env": {
"JIRA_URL": "https://jira.example.com",
"CONFLUENCE_URL": "https://confluence.example.com"
}
}
}
}
Codex (~/.codex/config.toml)
[mcp_servers.atlassian]
command = "uvx"
args = ["atlassian-browser-mcp"]
env = { JIRA_URL = "https://jira.example.com", CONFLUENCE_URL = "https://confluence.example.com" }
Protocol. Speaks MCP 2025-11-25, 2025-06-18, 2025-03-26 and 2024-11-05 over stdio, which covers clients that open with an initialize handshake (Claude Code, Claude Desktop, Cursor and VS Code today). MCP 2026-07-28 is not supported yet: upstream mcp-atlassian pins mcp<2 and fastmcp<4 (https://github.com/sooperset/mcp-atlassian/issues/1541), and this server follows as soon as upstream moves. It runs on stdio only and refuses to start with any other FASTMCP_TRANSPORT.
Read-only mode
Write tools act as you, with your SSO identity. To hide all of them (create, update, delete, transition, upload, restrictions), set READ_ONLY_MODE=true in the server's env. Upstream enforces it when listing and when calling. ENABLED_TOOLS (a comma-separated allow-list of tool names) and TOOLSETS narrow the list further; see Configuration.
Tools
| Tool | What it does | Hints |
|---|---|---|
atlassian_auth_status | Whether each service's saved session exists and works: jar age, cookie expiry, a live check, the next step | read-only |
atlassian_login | The exact atlassian-cli login <service> command to show the user | read-only |
jira_* (63) | Every upstream Jira tool: issues, search, comments, transitions, sprints, boards, versions, links, worklogs, attachments, service desk, forms | 38 read-only, 25 write |
confluence_* (35) | Every upstream Confluence tool: pages, search, comments, labels, attachments, history, templates, restrictions | 20 read-only, 15 write |
Every tool carries a title and all four annotation hints (read-only, destructive, idempotent, open-world), so clients can auto-approve reads and confirm writes. The full list and the CLI are in Usage.
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
Frequently asked questions
What is Atlassian (browser SSO)?
Jira and Confluence behind SSO via your own browser session: every mcp-atlassian tool, no API token
How do I install Atlassian (browser SSO)?
It runs on your machine. In Claude Code: claude mcp add atlassian-browser-sso -e 'JIRA_URL=<JIRA_URL>' -e 'CONFLUENCE_URL=<CONFLUENCE_URL>' -e 'READ_ONLY_MODE=<READ_ONLY_MODE>' -e 'ENABLED_TOOLS=<ENABLED_TOOLS>' -e 'ATLASSIAN_BROWSER_AUTH_ENABLED=<ATLASSIAN_BROWSER_AUTH_ENABLED>' -e 'ATLASSIAN_STORAGE_STATE=<ATLASSIAN_STORAGE_STATE>' -- uvx atlassian-browser-mcp==1.4.1. For other clients, paste the JSON configuration from this page into their MCP settings.
Does Atlassian (browser SSO) need an API key?
Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.
Is Atlassian (browser SSO) open source?
Yes. Its code is on GitHub under the GPL-3.0 license.
Who maintains Atlassian (browser SSO)?
It is published by GeiserX. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.