mcp-atlassian-extended
Install: uvx mcp-atlassian-extended | PyPI | MCP Registry | Changelog
mcp-atlassian-extended is a Model Context Protocol (MCP) server for Jira and Confluence. It gives an AI assistant 22 tools, 15 resources, and 5 prompts for Jira and Confluence work. The tools create and update issues with custom fields, link issues, manage attachments, and search users. They also run agile boards and sprints, track project versions (API v2), read team calendars, and plan sprint capacity. It extends mcp-atlassian with zero tool overlap.
The server supports the MCP 2026-07-28 specification (often called MCP 2.0) and stays compatible with 2025-11-25 clients. It works with Claude Desktop, Claude Code, Cursor, Windsurf, VS Code Copilot, and any MCP-compatible client.
The server supports Jira Cloud, Jira Data Center, Confluence Cloud, and Confluence Data Center (self-hosted). It needs no Atlassian Premium plan.
Built with FastMCP, httpx, and Pydantic.
Protocol support
- The server implements the MCP 2026-07-28 specification, often called MCP 2.0.
- It stays compatible with 2025-11-25 clients.
- Transports:
stdio (default) and streamable-http (recommended for remote clients). The sse transport still works, but the 2026-07-28 specification deprecates it, so the server prints a warning.
- The server uses no roots, sampling, logging, elicitation, or resource subscriptions. The 2026-07-28 deprecations do not affect it.
- Built on FastMCP 4.x and the MCP Python SDK 2.x.
Relationship to mcp-atlassian
This project runs alongside mcp-atlassian, not as a replacement. Configure both servers:
- mcp-atlassian handles: issues, search, transitions, comments, worklog, pages, Confluence search
- mcp-atlassian-extended handles: attachments, agile, users, fields, versions (API v2), calendars, time-off
There is no tool overlap — this server only implements tools that mcp-atlassian lacks.
1-Click Installation
💡 Tip: For other AI assistants (Claude Code, Windsurf, IntelliJ, Gemini CLI), visit the Atlassian Extended MCP Installation Gateway.
Manual Setup Guides (Click to expand)
Prerequisite: Install uv first (required for all uvx install flows). Install uv.
Claude Code
claude mcp add atlassian-extended -- uvx mcp-atlassian-extended
Windsurf & IntelliJ
Windsurf: Add to ~/.codeium/windsurf/mcp_config.json
IntelliJ: Add to Settings | Tools | MCP Servers
Note: The actual server config starts at atlassian-extended inside the mcpServers object.
{
"mcpServers": {
"atlassian-extended": {
"command": "uvx",
"args": ["mcp-atlassian-extended"],
"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"
}
}
}
}
Gemini CLI
gemini mcp add -e JIRA_URL=https://your-company.atlassian.net -e JIRA_USERNAME=your.email@company.com -e JIRA_API_TOKEN=your_api_token -e CONFLUENCE_URL=https://your-company.atlassian.net/wiki -e CONFLUENCE_USERNAME=your.email@company.com -e CONFLUENCE_API_TOKEN=your_api_token atlassian-extended uvx mcp-atlassian-extended
pip / uv
uv pip install mcp-atlassian-extended
Configuration
Jira Cloud (Basic Auth)
Jira Data Center / Self-Hosted (Bearer Token)
| Variable | Required | Default | Description |
|---|
JIRA_URL | Yes | - | Jira instance URL |
JIRA_PAT | Yes | - | Personal access token (see fallback order below) |
The server checks these environment variables in order — first match wins:
JIRA_PATJIRA_PERSONAL_TOKENJIRA_TOKEN
Basic auth wins. If you set both JIRA_USERNAME and JIRA_API_TOKEN, the server uses
Basic auth and ignores any personal access token. The server uses Bearer auth only when
the Cloud pair is incomplete. To force Bearer, unset JIRA_USERNAME and JIRA_API_TOKEN.
Confluence Cloud (Basic Auth)
| Variable | Required | Default | Description |
|---|
CONFLUENCE_URL | Yes | - | Confluence URL (e.g. https://your-company.atlassian.net/wiki) |
CONFLUENCE_USERNAME | Yes | - | Email address for Confluence Cloud |
CONFLUENCE_API_TOKEN | Yes | - | API token (same as Jira if same Atlassian account) |
Confluence Data Center / Self-Hosted (Bearer Token)
| Variable | Required | Default | Description |
|---|
CONFLUENCE_URL | Yes | - | Confluence instance URL |
CONFLUENCE_PAT | Yes | - | Personal access token (see fallback order below) |
The server checks these environment variables in order — first match wins:
CONFLUENCE_PATCONFLUENCE_PERSONAL_TOKENCONFLUENCE_TOKEN
Basic auth wins here too: CONFLUENCE_USERNAME + CONFLUENCE_API_TOKEN take precedence
over any personal access token.
All Confluence calendar tools require the Team Calendars add-on
(/rest/calendar-services/1.0/). On instances without it every calendar tool returns a
404 with a hint naming the add-on.
Optional settings
| Variable | Default | Description |
|---|
ATLASSIAN_READ_ONLY | false | Set to true to globally disable write operations across tools |
JIRA_TIMEOUT | 30 | HTTP request timeout for Jira in seconds |
JIRA_SSL_VERIFY | true | Set to false to skip SSL verification for Jira |
CONFLUENCE_TIMEOUT | 30 | HTTP request timeout for Confluence in seconds |
CONFLUENCE_SSL_VERIFY | true | Set to false to skip SSL verification for Confluence |
Compatibility
| Client | Supported | Install Method |
|---|
| Claude Desktop | Yes | claude_desktop_config.json |
| Claude Code | Yes | claude mcp add |
| Cursor | Yes | One-click deeplink or .cursor/mcp.json |
| Windsurf | Yes | ~/.codeium/windsurf/mcp_config.json |
| VS Code Copilot | Yes | .vscode/mcp.json |
| Any MCP client | Yes | stdio or HTTP transport |
| Category | Count | Tools |
|---|
| Jira Issues | 2 | create (with custom fields; issue_type="Epic" for epics), update (with custom fields) |
| Jira Links | 2 | create link, delete link |
| Jira Attachments | 4 | get, upload, download, delete |
| Jira Users | 1 | search by name/email |
| Jira Metadata | 3 | list projects, list fields, backlog |
| Jira Agile | 4 | get board, board config, get sprint, move to sprint |
| Jira Versions | 3 | get project versions, create version, update version |
| Confluence Calendars | 3 | list (type/search filter), time-off (date range, per-person), sprint capacity |
Full tool reference (click to expand)
Jira Issues
| Tool | Description |
|---|
jira_create_issue | Create issue with standard and custom fields (issue_type="Epic" creates an epic) |
jira_update_issue | Update issue fields and custom fields |
Jira Links
| Tool | Description |
|---|
jira_create_link | Create a link between two issues (Relates, Blocks, etc.) |
jira_delete_link | Delete an issue link by ID |
Jira Attachments
| Tool | Description |
|---|
jira_get_attachments | List attachments on an issue |
jira_upload_attachment | Upload file to issue |
jira_download_attachment | Download attachment to local file |
jira_delete_attachment | Delete an attachment |
Jira Users
| Tool | Description |
|---|
jira_search_users | Search users by name/email |
| Tool | Description |
|---|
jira_list_projects | List all accessible projects |
jira_list_fields | List fields (with search/custom filter) |
jira_backlog | Get backlog issues for a board |
Jira Agile
| Tool | Description |
|---|
jira_get_board | Get board details |
jira_board_config | Get board column configuration |
jira_get_sprint | Get sprint details |
jira_move_to_sprint | Move issues to a sprint |
Jira Versions
| Tool | Description |
|---|
jira_get_project_versions | List all versions for a project (REST API v2, Server/DC + Cloud) |
jira_create_version | Create a new version in a project (REST API v2) |
jira_update_version | Update an existing version (REST API v2) |
Confluence Calendars
| Tool | Description |
|---|
confluence_list_calendars | List calendars; optional filter_type and name/space search |
confluence_get_time_off | Time-off events for a date range; optional person (exact match) and group_by_person |
confluence_sprint_capacity | Calculate sprint capacity with time-off |
Resources (15)
The server exposes curated Jira and Confluence workflow guides as MCP resources.
| URI | Name | Description |
|---|
resource://rules/jira-hierarchy | Jira Issue Hierarchy | Epic/story/task/subtask relationships, when to use each level |
resource://rules/jira-ticket-writing | Jira Ticket Writing Standards | Summary format, description structure, acceptance criteria placement |
resource://rules/acceptance-criteria | Acceptance Criteria Standards | Given/When/Then format, testability, DoD vs AC |
resource://rules/sprint-hygiene | Sprint Hygiene Rules | Capacity planning, carryover policy, sprint goals, retrospective items |
resource://rules/jira-workflow | Jira Workflow & Automation | Status transitions, automation triggers, post-functions |
resource://rules/issue-linking | Issue Linking Best Practices | Link types (blocks, relates, duplicates), cross-project links, epic links |
resource://guides/story-points | Story Point Estimation | Fibonacci scale, relative sizing, team calibration, anti-patterns |
resource://guides/definition-of-done | Definition of Done Checklists | Checklist format, team-level vs org-level DoD, verification steps |
resource://guides/jira-labels | Jira Label Taxonomy | Naming conventions, label categories, label vs component |
resource://guides/jql-library | JQL Query Library | Common queries, date functions, custom field syntax, saved filters |
resource://guides/custom-fields | Jira Custom Field Governance | Field types, screen schemes, context, naming standards |
resource://guides/confluence-spaces | Confluence Space Organization | Space types, permission schemes, archiving, templates |
resource://guides/agile-ceremonies | Agile Ceremony Standards | Standup, planning, review, retro formats and time-boxing |
resource://guides/git-jira-integration | Git-Jira Integration Patterns | Smart commits, branch naming, PR linking, status transitions |
resource://templates/confluence-pages | Confluence Page Templates | ADR, runbook, onboarding, postmortem page structures |
Prompts (5)
The server provides MCP prompts — reusable multi-tool workflow templates that clients can surface as slash commands.
| Prompt | Parameters | Workflow |
|---|
create_ticket | project_key, issue_type | Gather fields → set custom fields (DoD, privacy, security) → create → add links |
plan_sprint | board_id, sprint_id | Check sprint → review backlog → calculate capacity → suggest scope → move issues |
close_ticket | issue_key | Verify DoD → check linked MR → transition statuses → add closing comment |
team_availability | team_members, start_date, end_date | Check who is out → per-person time-off → calculate capacity → flag conflicts |
manage_attachments | issue_key | List attachments → identify stale/duplicates → upload/download → clean up |
Usage Examples
Issue Management
"Create a story in PROJ with custom story points"
→ jira_create_issue(project_key="PROJ", summary="Add OAuth login", issue_type="Story",
custom_fields={"customfield_10004": 5})
"Update a ticket's priority and add labels"
→ jira_update_issue(issue_key="PROJ-123", fields={"priority": {"name": "High"}, "labels": ["urgent"]})
"Create an epic and link related stories"
→ jira_create_issue(project_key="PROJ", summary="Q1 Auth Overhaul", issue_type="Epic")
→ jira_create_link(link_type="Relates", inward_issue="PROJ-100", outward_issue="PROJ-200")
Attachments
"List attachments on PROJ-123"
→ jira_get_attachments(issue_key="PROJ-123")
"Upload a screenshot to a ticket"
→ jira_upload_attachment(issue_key="PROJ-123", file_path="./screenshot.png")
"Download an attachment"
→ jira_download_attachment(content_url="https://jira.example.com/rest/api/2/attachment/content/456",
save_path="./downloads/report.pdf")
Agile & Sprint Management
"Get the current sprint for board 42"
→ jira_get_board(board_id=42) → jira_get_sprint(sprint_id=7)
"Move tickets into the next sprint"
→ jira_move_to_sprint(sprint_id=8, issue_keys=["PROJ-1", "PROJ-2", "PROJ-3"])
"View backlog for board 42"
→ jira_backlog(board_id=42, max_results=50)
Version Management
"List versions for project PROJ"
→ jira_get_project_versions(project_key="PROJ")
"Create a new release version"
→ jira_create_version(project_key="PROJ", name="v2.0.0", release_date="2026-04-01")
"Mark version as released"
→ jira_update_version(version_id="200", released=True)
Time-Off & Sprint Capacity
"Who is out today?"
→ confluence_get_time_off(start_date="today", end_date="today", group_by_person=True)
"Get team time-off for the next two weeks"
→ confluence_get_time_off(start_date="today", end_date="+14d", group_by_person=True)
"Calculate sprint capacity accounting for PTO"
→ confluence_sprint_capacity(
team_members=["Alice", "Bob", "Carol"],
sprint_start="2025-03-03", sprint_end="2025-03-14")
Security Considerations
- Token scope: For Jira Cloud, use API tokens scoped to the minimum required permissions. For Data Center, use PATs with project-level access.
- Read-only mode: Set
ATLASSIAN_READ_ONLY=true to disable all write operations (create, update, delete, upload). The server enforces this before any API call.
- File upload validation:
jira_upload_attachment validates file paths (no traversal, max 100MB, file must exist).
- Download path restriction:
jira_download_attachment accepts only relative paths resolved within the working directory. It rejects absolute paths and path traversal (../).
- Download URL validation: The server validates each attachment download URL against the configured Jira URL domain to prevent SSRF.
- SSL verification: The server enables SSL verification by default for Jira and Confluence. Disable it only for self-signed certificates in trusted networks.
- MCP tool annotations: Each tool declares
readOnlyHint, destructiveHint, and idempotentHint for client-side permission prompts.
- No credential storage: The server reads tokens from environment variables at startup. It never stores them.
Rate Limits & Permissions
Rate Limits
Jira Cloud enforces per-user rate limits. When rate-limited, tools return a 429 error with a hint to wait. Confluence Calendar API calls may be slower due to the Team Calendars plugin architecture.
Required Permissions
| Operation | Minimum Jira Permission |
|---|
| List projects, fields, boards | Browse Projects |
| Search users | Browse Users |
| Create/update issues, epics | Create Issues + Edit Issues |
| Create/delete issue links | Link Issues |
| Upload/delete attachments | Create Attachments + Delete Own Attachments |
| Move issues to sprint | Manage Sprints |
| Create/update versions | Administer Projects |
| Confluence calendars/time-off | View space content |
CLI & Transport Options
uvx mcp-atlassian-extended
uvx mcp-atlassian-extended --transport streamable-http --port 9000
uvx mcp-atlassian-extended --transport sse --host 127.0.0.1 --port 8000
uvx mcp-atlassian-extended --jira-url https://jira.example.com --jira-token xxx --read-only
The server loads .env files from the working directory automatically via python-dotenv.
Partial configuration: You configure Jira and Confluence independently. Set either or both. The server always advertises all 22 tools. A tool for an unconfigured product returns a "not configured" error that names the variables to set. The server does not fail at startup.
FAQ
Does it support the MCP 2026-07-28 spec (MCP 2.0)?
Yes. It implements the MCP 2026-07-28 specification (MCP 2.0) and stays compatible with 2025-11-25 clients.
Which transports does it support?
It supports stdio (the default) and streamable-http (recommended for remote clients). The sse transport still works, but the 2026-07-28 specification deprecates it.
Is it read-only safe?
Yes. Set ATLASSIAN_READ_ONLY=true to disable every write operation. The server enforces this before any API call.
Does it work with self-hosted Jira and Confluence?
Yes. It supports Jira Cloud, Jira Data Center, Confluence Cloud, and Confluence Data Center. It uses the Jira REST API v2, which works on both Cloud and Server/Data Center.
What permissions and token scopes does it need?
It needs a Jira API token (Cloud) or a personal access token (Data Center). Each operation needs the matching Jira permission. See Required Permissions.
Does it replace mcp-atlassian?
No. It runs alongside mcp-atlassian with zero tool overlap. mcp-atlassian handles core search and CRUD. This server adds attachments, agile boards, versions, and calendars.
Yes. The three Confluence calendar tools need the Team Calendars add-on. Without it, they return a 404 with a hint that names the add-on.
It provides 22 tools, 15 resources, and 5 prompts for Jira and Confluence.
- mcp-gitlab — GitLab integration (76 tools, 6 resources, 5 prompts)
- mcp-coda — Coda.io integration (54 tools, 12 resources, 5 prompts)
Attribution
Inspired by mcp-atlassian by sooperset. Architecture and patterns follow similar conventions.
Development
git clone https://github.com/vish288/mcp-atlassian-extended.git
cd mcp-atlassian-extended
uv sync --all-extras
uv run pytest --cov
uv run ruff check .
uv run ruff format --check .
License
MIT