Jira Extended MCP Server
Provides tools for Jira issue management, including full CRUD, bulk operations, sprint and release management, issue linking, and rich text support using Jira wiki markup.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Jira Extended MCP Server Show me all high priority issues in the KAN project"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Built by Moobean Team — a lightweight, Jira-only MCP server focused on getting things done with minimal setup.
What Makes This Different
Jira-only, zero bloat — No Confluence, no extra modules. One
uvxcommand and you're running.Wiki markup support — Uses Jira REST API v2, so
*bold*,h2. Title,* bulletjust work. No ADF JSON hassle.Bulk operations — Create up to 50 issues or transition multiple issues in a single call.
Full release lifecycle — Create, update, delete versions and assign issues to releases.
Issue links — Block, relate, duplicate, clone — with create, query, and delete support.
Related MCP server: jira-mcp-server
Comparison
Note: Feature data is based on each project's README and documentation as of March 2026. Features may have changed since then.
Jira Extended | ||||
Scope | Jira only | Jira + Confluence | Jira + Confluence + Compass | Jira only |
Issue CRUD | Read-only | Full CRUD | Full CRUD | Full CRUD |
Bulk Create | - | Supported | Supported | 50 issues/call |
Bulk Transition | - | - | - | Supported |
Parent / Sub-task | - | Supported | Supported | Supported |
fixVersions | - | Supported | Supported | Supported |
startDate / dueDate | - | Supported | Supported | Supported |
Issue Links | - | Supported | - | Supported |
Release Management | - | - | - | 4 tools |
Sprint Management | - | Supported | - | Supported |
Rich Text | - | Markdown → ADF | ADF | Wiki markup (v2 API) |
Setup | npm | pip / Docker | OAuth (cloud-hosted) |
|
Total Jira Tools | 2 | ~30 (Jira portion) | ~25 (Jira portion) | 27 |
Language | TypeScript | Python | Remote (SaaS) | Python |
Use Cases
Just ask your AI agent in natural language:
Issue Management
"Create an epic in the KAN project titled 'User Auth System', start date April 1st, due date April 30th"
"Create 5 stories under KAN-42: Login, Sign Up, Password Reset, Social Login, 2FA"
"Show me all 'In Progress' issues in the KAN project"
Bulk Operations
"Transition all 10 backlog issues in this sprint to 'Done'"
"Show me the issue list included in the v2.0 release"
Releases & Sprints
"Create a v2.1.0 release in KAN project with release date May 15th"
"Move KAN-50 and KAN-51 to the current active sprint"
Issue Links
"Link KAN-10 as blocking KAN-20"
Rich Text (Wiki Markup)
"Create an issue with h2 headings and bullet lists in the description"
Quick Start
Prerequisites
uv(Python package manager — installs Python automatically if needed)
Step 1: Install uv
uv is a Python package manager. If you don't have it:
# macOS / Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
# Windows (PowerShell)
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"Step 2: Get a Jira API Token
Go to https://id.atlassian.com/manage-profile/security/api-tokens
Click Create API token
Copy the token — you'll need it in the next step
Step 3: Configure your AI client
Choose where to add the config:
Scope | File | Effect |
Global (recommended) |
| Available in all projects |
Project only |
| Only in that project |
Easiest — one command:
# macOS / Linux
claude mcp add jira-extended -s user \
-e JIRA_URL=https://your-instance.atlassian.net \
-e JIRA_EMAIL=your-email@example.com \
-e JIRA_API_TOKEN=your-token \
-- uvx jira-extended-mcp
# Windows — use uvx.exe (not uvx) to avoid .cmd wrapper issues
claude mcp add jira-extended -s user \
-e JIRA_URL=https://your-instance.atlassian.net \
-e JIRA_EMAIL=your-email@example.com \
-e JIRA_API_TOKEN=your-token \
-- uvx.exe jira-extended-mcp
-s userinstalls globally. Omit it for project-only install.
Or edit the config file manually:
Open the file in a text editor:
# macOS / Linux
code ~/.claude.json # or: nano ~/.claude.json
# Windows
notepad %USERPROFILE%\.claude.jsonAdd this content (create the file if it doesn't exist):
{
"mcpServers": {
"jira-extended": {
"command": "uvx",
"args": ["jira-extended-mcp"],
"env": {
"JIRA_URL": "https://your-instance.atlassian.net",
"JIRA_EMAIL": "your-email@example.com",
"JIRA_API_TOKEN": "your-api-token"
}
}
}
}Windows users: Use
"command": "uvx.exe"instead of"command": "uvx". Theuvx.cmdwrapper on Windows breaks the MCP stdio transport.
Open the config file in a text editor:
# macOS
code ~/Library/Application\ Support/Claude/claude_desktop_config.json
# Windows
notepad %APPDATA%\Claude\claude_desktop_config.jsonAdd or merge into the file:
{
"mcpServers": {
"jira-extended": {
"command": "uvx",
"args": ["jira-extended-mcp"],
"env": {
"JIRA_URL": "https://your-instance.atlassian.net",
"JIRA_EMAIL": "your-email@example.com",
"JIRA_API_TOKEN": "your-api-token"
}
}
}
}If the file already has other MCP servers, add the
"jira-extended": {...}block inside the existing"mcpServers"object.Windows users: Use
"command": "uvx.exe"instead of"command": "uvx".
Create .vscode/mcp.json in your project root:
mkdir -p .vscode
code .vscode/mcp.json{
"servers": {
"jira-extended": {
"command": "uvx",
"args": ["jira-extended-mcp"],
"env": {
"JIRA_URL": "https://your-instance.atlassian.net",
"JIRA_EMAIL": "your-email@example.com",
"JIRA_API_TOKEN": "your-api-token"
}
}
}
}Enable MCP: Settings > Chat > MCP must be checked. Works in Agent mode.
Windows users: Use
"command": "uvx.exe"instead of"command": "uvx".
Open the config file:
# macOS / Linux
code ~/.cursor/mcp.json
# Windows
notepad %USERPROFILE%\.cursor\mcp.json{
"mcpServers": {
"jira-extended": {
"command": "uvx",
"args": ["jira-extended-mcp"],
"env": {
"JIRA_URL": "https://your-instance.atlassian.net",
"JIRA_EMAIL": "your-email@example.com",
"JIRA_API_TOKEN": "your-api-token"
}
}
}
}Windows users: Use
"command": "uvx.exe"instead of"command": "uvx".
git clone https://github.com/moobean-team/jira-extended-mcp-server.git
cd jira-extended-mcp-server
uv pip install -e .Then use "command": "jira-extended-mcp" instead of "command": "uvx" in your config.
Step 4: Restart & verify
Restart your AI client, then ask:
"Show my Jira projects"
If you see your project list, you're all set.
Configuration
Environment Variables
Variable | Required | Default | Description |
| Yes | — | Jira Cloud instance URL |
| Yes | — | Atlassian account email |
| Yes | — | |
| No |
| Custom field ID for start date |
Finding Your Start Date Field ID
The start date field ID varies per Jira instance. Use the get_createmeta tool for your project to see available fields, or:
curl -s -u email:token https://your-instance.atlassian.net/rest/api/2/field \
| python -m json.tool | grep -i "start"Rich Text (Wiki Markup)
This server uses Jira REST API v2, which accepts Jira wiki markup strings for description and comment fields. Jira renders them as rich text automatically.
Syntax | Renders as |
| bold |
| italic |
| H2 heading |
| Bullet list |
| Numbered list |
| Code block |
| Hyperlink |
| Table |
Full reference: Jira Wiki Markup
Available Tools
Tool | Description |
| Create issue with full field support — parent, fixVersions, startDate, dueDate, story points, components, custom fields |
| Bulk create up to 50 issues in a single API call |
| Get issue details with formatted output |
| Update any issue field (only changed fields are sent) |
| Delete issue with subtask handling |
| JQL search with pagination and configurable fields |
Tool | Description |
| List available status transitions for an issue |
| Change issue status by name or ID, with optional comment |
| Transition multiple issues at once |
Tool | Description |
| Create link between issues (Blocks, Relates, Duplicate, Cloners) |
| Get all links for an issue with link type details |
| Remove a link by ID |
Tool | Description |
| List project versions/releases |
| Create a new release with start/release dates |
| Update release details, mark as released/archived |
| Delete a release with issue reassignment options |
Tool | Description |
| List sprints for a board (filter by active/future/closed) |
| Move issues to a target sprint |
Tool | Description |
| Add comment to an issue (supports wiki markup) |
| Get issue comments with author and timestamps |
| Log work time with human-friendly format ("2h 30m", "1d") |
Tool | Description |
| List all accessible projects |
| Get project details |
| List boards (scrum/kanban/simple) |
| Get authenticated user info |
| Search users by name/email |
| Get available issue types and fields per project |
Architecture
src/jira_extended_mcp/
├── server.py # FastMCP server + 27 tool definitions
├── client.py # Async Jira REST client (httpx + rate limit retry)
├── adf.py # ADF fallback helpers (v3 response parsing)
└── __init__.pyKey design decisions:
Decision | Why |
REST API v2 for issues/comments | v2 accepts wiki markup strings for rich text. v3 requires ADF JSON which strips formatting |
REST API v3 for metadata | Versions, projects, users don't have text fields — v3 is fine |
Agile API for sprints/boards | Sprint ops are only available via |
FastMCP lifespan |
|
Structured errors | Errors return |
Configurable start date field |
|
Development
git clone https://github.com/moobean-team/jira-extended-mcp-server.git
cd jira-extended-mcp-server
uv pip install -e .
# Run directly
jira-extended-mcp
# Or via module
python -m jira_extended_mcp.serverTroubleshooting
Ensure JIRA_URL, JIRA_EMAIL, and JIRA_API_TOKEN are set in your MCP config's env block. The server checks these on startup.
Jira transitions are workflow-specific. Use get_transitions first to see available transitions for the issue's current status. Transition names are case-insensitive.
Your Jira instance may use a different custom field ID. Use get_createmeta to find the correct field, then set JIRA_START_DATE_FIELD env var.
The server automatically retries up to 3 times using the Retry-After header. For bulk operations with 50+ issues, consider splitting into multiple calls.
This server uses Jira REST API v2 which accepts wiki markup. Use Jira wiki syntax (*bold*, h2. Title, * bullet) instead of Markdown.
License
MIT © Moobean Team
Available Tools
27 toolsadd_commentB
Add a comment to an issue.
Args: issue_key: Issue key (e.g., "KAN-123") body: Comment text (plain text, supports Jira wiki markup for rich text)
Inputs: body (required), issue_key (required). Returns: object
add_worklogB
Add a worklog entry to an issue.
Args: issue_key: Issue key (e.g., "KAN-123") time_spent: Time spent string (e.g., "2h 30m", "1d", "4h") comment: Work description started: Start time in ISO format (e.g., "2026-03-24T09:00:00.000+0000")
Inputs: issue_key (required), time_spent (required), comment, started. Returns: object
bulk_transitionC
Transition multiple issues to a new status.
Args: issue_keys: List of issue keys (e.g., ["KAN-1", "KAN-2"]) transition_name: Target transition name (e.g., "Done") comment: Optional comment for all transitions
Inputs: issue_keys (required), transition_name (required), comment. Returns: object
create_issueB
Create a Jira issue with full field support including parent, fixVersions, dates.
Args: project: Project key (e.g., "KAN") issue_type: Issue type name (e.g., "Task", "Story", "Bug", "Epic") summary: Issue title description: Plain text description (supports Jira wiki markup for rich text) assignee_id: Atlassian account ID of assignee priority: Priority name (e.g., "High", "Medium", "Low") labels: List of label strings parent: Parent issue key for sub-tasks or stories under epics (e.g., "KAN-1") fix_versions: List of version names (e.g., ["v1.0.0"]) components: List of component names start_date: Start date in YYYY-MM-DD format due_date: Due date in YYYY-MM-DD format story_points: Story point estimate custom_fields: Dict of custom field IDs to values
Inputs: project (required), summary (required), issue_type (required), labels, +10 more. Returns: object
create_issues_bulkA
Create multiple issues in bulk (max 50 per request).
Args: issues: List of issue objects. Each must have: project, issue_type, summary. Optional: description, assignee_id, priority, labels, parent, fix_versions, components, start_date, due_date, custom_fields.
Inputs: issues (required). Returns: object
create_versionB
Create a new version/release in a project.
Args: project_key: Project key (e.g., "KAN") name: Version name (e.g., "v1.0.0") description: Version description start_date: Start date (YYYY-MM-DD) release_date: Release date (YYYY-MM-DD)
Inputs: name (required), project_key (required), start_date, description, +1 more. Returns: object
delete_issueB
Delete a Jira issue.
Args: issue_key: Issue key (e.g., "KAN-123") delete_subtasks: Also delete subtasks (default: True)
Inputs: issue_key (required), delete_subtasks. Returns: object
delete_issue_linkB
Delete an issue link by its ID.
Args: link_id: The link ID (get from get_issue_links)
Inputs: link_id (required). Returns: object
delete_versionB
Delete a version/release.
Args: version_id: Version ID to delete move_fix_issues_to: Version ID to reassign fix version issues move_affected_issues_to: Version ID to reassign affected version issues
Inputs: version_id (required), move_fix_issues_to, move_affected_issues_to. Returns: object
get_boardsB
List Jira boards.
Args: project_key: Filter by project key board_type: Filter by type: "scrum", "kanban", "simple"
Inputs: board_type, project_key. Returns: object
get_commentsB
Get comments on an issue.
Args: issue_key: Issue key (e.g., "KAN-123") max_results: Maximum number of comments (default 50)
Inputs: issue_key (required), max_results. Returns: object
get_createmetaA
Get issue creation metadata for a project (available issue types and fields).
Args: project_key: Project key (e.g., "KAN")
Inputs: project_key (required). Returns: object
get_current_userA
Get the currently authenticated Jira user.
Inputs: no named parameters. Returns: object
get_issueB
Get detailed information about a Jira issue.
Args: issue_key: Issue key (e.g., "KAN-123") fields: Comma-separated field names to include (default: all) expand: Comma-separated expansions (e.g., "changelog,transitions")
Inputs: issue_key (required), expand, fields. Returns: object
get_issue_linksA
Get all links for an issue.
Args: issue_key: Issue key (e.g., "KAN-123")
Inputs: issue_key (required). Returns: object
get_projectB
Get detailed information about a project.
Args: project_key: Project key (e.g., "KAN")
Inputs: project_key (required). Returns: object
get_projectsB
List all accessible Jira projects.
Inputs: no named parameters. Returns: object
get_sprintsB
Get sprints for a board.
Args: board_id: Board ID state: Filter by state: "future", "active", "closed" (default: all)
Inputs: board_id (required), state. Returns: object
get_transitionsB
Get available status transitions for an issue.
Args: issue_key: Issue key (e.g., "KAN-123")
Inputs: issue_key (required). Returns: object
get_versionsB
Get all versions/releases for a project.
Args: project_key: Project key (e.g., "KAN")
Inputs: project_key (required). Returns: object
link_issuesB
Create a link between two issues.
Args: inward_issue: Inward issue key (e.g., "KAN-1") outward_issue: Outward issue key (e.g., "KAN-2") link_type: Link type name (e.g., "Blocks", "Relates", "Duplicate", "Cloners") comment: Optional comment
Inputs: inward_issue (required), outward_issue (required), comment, link_type. Returns: object
move_to_sprintC
Move issues to a sprint.
Args: sprint_id: Target sprint ID issue_keys: List of issue keys to move (e.g., ["KAN-1", "KAN-2"])
Inputs: sprint_id (required), issue_keys (required). Returns: object
search_issuesB
Search Jira issues using JQL.
Args: jql: JQL query string (e.g., 'project = KAN AND status = "To Do"') fields: Comma-separated fields to return max_results: Maximum results (1-100, default 50) next_page_token: Token for next page (from previous response)
Inputs: jql (required), fields, max_results, next_page_token. Returns: object
search_usersC
Search for Jira users by name or email.
Args: query: Search string (name, email, or display name) max_results: Maximum results (default 25)
Inputs: query (required), max_results. Returns: object
transition_issueB
Transition an issue to a new status.
Args: issue_key: Issue key (e.g., "KAN-123") transition_name: Transition name (e.g., "In Progress", "Done"). Used to auto-find ID. transition_id: Transition ID (takes priority over name) comment: Optional comment to add during transition resolution: Optional resolution name (e.g., "Done") for closing transitions
Inputs: issue_key (required), comment, resolution, transition_id, +1 more. Returns: object
update_issueA
Update an existing Jira issue. Only provided fields are changed.
Args: issue_key: Issue key (e.g., "KAN-123") summary: New summary description: New description (plain text, supports Jira wiki markup for rich text) assignee_id: New assignee account ID priority: New priority name labels: Replace all labels fix_versions: Replace all fix versions (list of version names) components: Replace all components start_date: New start date (YYYY-MM-DD) due_date: New due date (YYYY-MM-DD) parent: New parent issue key story_points: New story point estimate custom_fields: Dict of custom field IDs to values
Inputs: issue_key (required), labels, parent, summary, +9 more. Returns: object
update_versionB
Update an existing version/release.
Args: version_id: Version ID (get from get_versions) name: New version name description: New description start_date: New start date (YYYY-MM-DD) release_date: New release date (YYYY-MM-DD) released: Mark as released archived: Mark as archived
Inputs: version_id (required), name, archived, released, +3 more. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 27 tools
Each tool targets a distinct Jira resource or action; single vs. bulk variants (create_issue vs. create_issues_bulk, transition_issue vs. bulk_transition) are clearly distinguished by descriptions. No meaningful overlap would cause misselection.
Names are consistently snake_case and mostly follow a verb_noun pattern. Minor deviations exist: bulk_transition uses a prefix while create_issues_bulk uses a suffix, and get_createmeta compresses a Jira term, but the set remains predictable.
27 tools is heavy for an MCP server and exceeds the typical 3-15 range. However, the breadth is aligned with an 'extended' Jira surface covering issues, versions, sprints, comments, worklogs, projects, and boards, so it is over-scoped rather than redundant.
Core issue lifecycle is well covered (CRUD, search, transitions, bulk operations, links), and versions have full CRUD. Gaps remain in secondary areas: comments only support add/get, worklogs only support add, and sprints/boards lack full lifecycle management.
Maintenance
Related MCP Connectors
Connect to Atlassian Jira, Confluence, Loom, and more to search, create, and manage your work.
Task manager your agent can fully operate: boards, tasks, sprints, roles, worklogs, day planner.
Manage Jensi projects, tasks, sprints and the AI suggestion inbox from your AI assistant.
Tasks, sprints, releases and docs for engineering teams with AI coding agents.
Related MCP Servers
- AlicenseAqualityNot gradedmaintenanceEnables AI assistants to interact with Atlassian Jira Cloud, allowing users to manage projects, issues, comments, and workflows through natural language commands.61,667 npm3-
- AlicenseBqualityDmaintenanceEnables AI agents to manage Jira projects and issues using natural language, including creating, updating, searching issues, managing sprints, and more via the Jira API.361,667 npm1MIT
- AlicenseAqualityDmaintenanceEnables AI agents to interact with Jira Cloud and Confluence through natural language, performing JQL searches, issue management, and Confluence page creation.106 npm1MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with Jira Cloud issues, supporting create, read, update, delete, search, and transition operations via natural language.40 npmMIT