atlassian-browser-mcp
This server provides comprehensive Atlassian integration (Jira + Confluence) with browser-based SSO authentication, enabling AI agents to interact with corporate Atlassian instances behind Okta/SAML/Azure AD/MFA.
Authentication
Launch a visible Chromium browser (
atlassian_login) for manual SSO/MFA login; cookies are persisted and sessions auto-renewed
Jira – Issues
Search with JQL, get/create/update/delete issues, batch-create issues
Get changelogs (Cloud only), download attachments, retrieve images as base64
Jira – Projects & Fields
List projects, get versions/components, create fix versions
Search fields with fuzzy matching, get custom field options
Jira – Workflows & Transitions
Get available transitions and transition issues to a new status
Jira – Comments, Worklogs & Watchers
Add/edit comments, get/add worklogs, get/add/remove watchers
Jira – Links & Epics
Get link types, create/remove issue links, create remote/web links, link issues to epics
Jira – Agile / Sprints
Get boards (Scrum/Kanban), board issues/sprints; create/update sprints and manage sprint issues
Jira – Service Desk (Server/DC only)
Get service desk info, queues, and queue issues
Jira – Forms (ProForma)
Get forms on an issue, retrieve form details, update form answers
Jira – Metrics & SLA
Get issue date/status transition history; calculate cycle time, lead time, time-in-status, etc.
Jira – Development Info
Get linked PRs, branches, and commits for one or multiple issues
Jira – Users
Get user profile by email, username, or account ID
Confluence – Pages
Search (text or CQL), get/create/update/delete/move pages
Get page children, full space page tree, version history, and diffs between versions
Confluence – Comments & Labels
Get/add comments, reply to threads, get/add labels
Confluence – Attachments
List, upload (single or batch), download, delete attachments; get images as inline base64
Confluence – Users & Analytics
Search users; get page view statistics (Cloud only)
73 tools total (72 upstream + 1 auth helper), supporting both read-only and write operations.
Provides browser-based authentication and API access for Atlassian Server/Data Center instances behind corporate SSO, enabling interaction with Atlassian services when API tokens are unavailable.
Enables programmatic access to Confluence instances via browser-cookie authentication, allowing AI agents to interact with Confluence content and features through the full mcp-atlassian toolset.
Provides browser-authenticated access to Jira instances, enabling AI agents to use the complete mcp-atlassian Jira toolset for managing issues, projects, and workflows.
Supports authentication through Okta SSO systems as part of the browser-based login flow for accessing Atlassian services behind corporate authentication.
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.SessionsubclassIf 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 |
| Entrypoint. Patches upstream clients, registers |
| Shared auth: |
| Launcher: creates venv, installs deps via |
| Dependency pins |
Usage
./run-atlassian-browser-mcp.shOr configure as an MCP server in your editor (Cursor, Claude Code, etc.) pointing to the launcher script.
Environment variables
Variable | Default | Description |
| (required) | Jira base URL (e.g. |
| (required) | Confluence base URL (e.g. |
|
| Enable browser auth (set |
|
| Persistent Chromium profile directory |
|
| Playwright storage-state file |
|
| Seconds to wait for manual login |
| (none) | Optional: prefill username on SSO page |
| (auto) | Comma-separated URL/text markers for SSO redirect detection. Defaults cover Okta, ADFS, Azure AD, PingOne, Google SAML |
|
| Which upstream toolsets to enable |
Requirements
Python 3.12+
uv (for dependency management)
Chromium (installed automatically by Playwright)
Network access to your Atlassian instance
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/GeiserX/atlassian-browser-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server