MCP Atlassian

Model Context Protocol (MCP) server for Atlassian products (Confluence and Jira). Supports both Cloud and Server/Data Center deployments.

mcp-atlassian-jira-demo.mp4

Confluence Demo

confluence-1k.mp4

Quick Start

1. Get Your API Token

Go to https://id.atlassian.com/manage-profile/security/api-tokens and create a token.

For Server/Data Center, use a Personal Access Token instead. See Authentication.

2. Configure Your IDE

Add to your Claude Desktop or Cursor MCP configuration:

{
  "mcpServers": {
    "mcp-atlassian": {
      "command": "uvx",
      "args": ["mcp-atlassian"],
      "env": {
        "JIRA_URL": "https://your-company.atlassian.net",
        "JIRA_USERNAME": "your.email@company.com",
        "JIRA_API_TOKEN": "your_api_token",
        "CONFLUENCE_URL": "https://your-company.atlassian.net/wiki",
        "CONFLUENCE_USERNAME": "your.email@company.com",
        "CONFLUENCE_API_TOKEN": "your_api_token"
      }
    }
  }
}

Server/Data Center users: Use JIRA_PERSONAL_TOKEN instead of JIRA_USERNAME + JIRA_API_TOKEN. See Authentication for details.

3. Start Using

Ask your AI assistant to:

• "Find issues assigned to me in PROJ project"
• "Search Confluence for onboarding docs"
• "Create a bug ticket for the login issue"
• "Update the status of PROJ-123 to Done"

Documentation

Full documentation is available at mcp-atlassian.soomiles.com.

Documentation is also available in llms.txt format, which LLMs can consume easily:

• llms.txt — documentation sitemap
• llms-full.txt — complete documentation

Topic	Description
Installation	uvx, Docker, pip, from source
Authentication	API tokens, PAT, OAuth 2.0
Configuration	IDE setup, environment variables
HTTP Transport	SSE, streamable-http, multi-user
Tools Reference	All Jira & Confluence tools
Troubleshooting	Common issues & debugging

Compatibility

Product	Deployment	Support
Confluence	Cloud	Fully supported
Confluence	Server/Data Center	Supported (v6.0+)
Jira	Cloud	Fully supported
Jira	Server/Data Center	Supported (v8.14+)

Key Tools

Jira	Confluence
jira_search - Search with JQL	confluence_search - Search with CQL
jira_get_issue - Get issue details	confluence_get_page - Get page content
jira_create_issue - Create issues	confluence_create_page - Create pages
jira_update_issue - Update issues	confluence_update_page - Update pages
jira_transition_issue - Change status	confluence_add_comment - Add comments

72 tools total — See Tools Reference for the complete list.

Jira DC Analyst toolset (this fork)

This fork adds 118 read-only deep-inspection tools for Jira Data Center admins, ported from jira-analyst-mcp. They cover configuration areas the stock REST API cannot see.

Full tool-by-tool list with descriptions → TOOLS.md.

Toolset	Tools	What it exposes
jira_analyst_admin	45	Workflows + raw XML, transitions (conditions/validators/post-functions), screens, screen schemes, permission / notification / workflow / field-config / issue-security schemes, groups, roles, application-role licensing, priority schemes, cluster info, my_permissions, get_reindex_status
jira_analyst_scriptrunner	11	Listeners, behaviours, scripted fields, fragments, jobs, REST endpoints, escalation services — with full Groovy source
jira_analyst_jmwe	4	JMWE event-based actions + shared actions
jira_analyst_structure	7	ALM Works Structure plugin + Structure-Gantt configs
jira_analyst_assets	10	Insight/Assets CMDB: schemas, object types, AQL search, imports
jira_analyst_automation	2	Automation for Jira (A4J) rule inspection
jira_analyst_logs	2	/rest/auditing/1.0/events + atlassian-jira.log tail
jira_analyst_integrations	6	Integration surface: UPM plugins (list/get/modules), webhooks (v1.0 + v10.x fallback), application links, dark features
jira_analyst_issue_inspect	4	Deep issue inspection: inline attachment content (image vision + text), thumbnails, votes, remote links
jira_analyst_dvcs	10	DVCS + Git integration story: native /rest/bitbucket/1.0 orgs/repos/sync audit, BigBrassBand Git Integration per-issue commits/branches/reverse-lookup, dev-status /summary + /detail that drive the issue Git panel
jira_analyst_properties	6	Entity-properties inspection — the generic JSON-blob storage used by Jira and many plugins (JXL sheets, Automation, scripting state) on projects, issues, and users. Read-only list + get for all three scopes
jira_analyst_sla	3	Appfire/SaaSJet Time to SLA plugin: list_sla_definitions, list_sla_calendars, search_sla_status (per-issue elapsed/remaining/breached across a JQL)
jira_analyst_time_in_status	3	OBSS Timepiece — Time in Status plugin: get_issue_time_in_status, search_time_in_status (list/average/sum modes via /api/list2), list_tis_calendars
jira_analyst_email	5	MetaInf Email This Issue (JETI) via /rest/jeti/1.0/: search_jeti_audit_log (who got what email when), get_jeti_audit_count, plus outgoing/incoming/generation mail-queue stats (v9.0.0+)

Enabling it

1. Install the Groovy REST endpoint on your Jira DC — copy scriptrunner/admin_analyst.groovy into a ScriptRunner custom REST endpoint exposed at /rest/scriptrunner/latest/custom/adminAnalyst (override with JIRA_ANALYST_SR_PATH).
2. Authenticate as usual (JIRA_URL + JIRA_PERSONAL_TOKEN) — the analyst client reuses the existing mcp-atlassian session.
3. Enable the toolsets you need via TOOLSETS, e.g. TOOLSETS=default,jira_analyst_admin,jira_analyst_scriptrunner.

All analyst toolsets are opt-in (default=false) and tagged read, so they stay invisible unless explicitly enabled and survive READ_ONLY_MODE=true. Plugin-specific tools (SR, JMWE, Structure, Assets, A4J) only work if the corresponding plugin is installed on the target instance.

Security

Never share API tokens. Keep .env files secure. See SECURITY.md.

Contributing

See CONTRIBUTING.md for development setup.

License

MIT - See LICENSE. Not an official Atlassian product.