Automated summary
This skill enables interaction with JIRA and Confluence from coding agents using the official Atlassian MCP server.
Strengths
- Direct access to JIRA issues and Confluence pages from the IDE.
- Common operations (create, edit, transition) easily scriptable.
- Built-in advanced search with JQL.
- Centralized configuration via mcp.json.
Limitations
- Requires prior OAuth authentication with Atlassian.
- Depends on the external MCP server availability.
- Confluence features are limited compared to the full API.
Use this skill when you need to view or modify JIRA issues directly from your development environment.
Avoid using it for bulk operations or when offline, since the server is external.
Security analysis
SafeThe skill documents setup and usage of an official Atlassian MCP server for JIRA and Confluence interactions. No destructive commands, remote code execution, or data exfiltration instructions are present. All operations are performed through a controlled API, and authentication is handled via OAuth.
No concerns found
How this analysis is madeExamples
Get details of JIRA issue PROJ-123 using the Atlassian MCP server.Search for JIRA issues in project PROJ with component 'backend' and status 'In Progress' using JQL.Create a new JIRA issue in project PROJ with issue type 'Story', summary 'Implement login feature', and component 'auth'.name: atlassian-mcp description: Use the Atlassian MCP Server to interact with JIRA from coding agents (Cursor, Claude Code). This skill documents how to use the official Atlassian MCP server for JIRA and Confluence operations. Enable this MCP server in your Cursor/Claude Code settings for JIRA access. requires:
- atlassian-oauth
Atlassian MCP Server for JIRA
The Atlassian MCP Server provides direct access to JIRA and Confluence from coding agents. This is the supported way to access Atlassian data from Cursor or Claude Code.
Setup
In Cursor
The Atlassian MCP Server is already configured globally. To enable it:
- Open Cursor Settings
- Go to Tools & MCP
- Enable "Atlassian-MCP-Server"
Configuration location: ~/.cursor/mcp.json
{
"mcpServers": {
"Atlassian-MCP-Server": {
"url": "https://mcp.atlassian.com/v1/sse"
}
}
}
In Claude Code
Add to your Claude Code MCP settings:
{
"mcpServers": {
"Atlassian-MCP-Server": {
"url": "https://mcp.atlassian.com/v1/sse"
}
}
}
Available Tools
When enabled, the Atlassian MCP Server provides these tools:
Issue Operations
| Tool | Description |
| ---------------------------------------- | ------------------------------- |
| mcp_Atlassian_getJiraIssue | Get details of a specific issue |
| mcp_Atlassian_createJiraIssue | Create a new issue |
| mcp_Atlassian_editJiraIssue | Update an existing issue |
| mcp_Atlassian_transitionJiraIssue | Change issue status |
| mcp_Atlassian_searchJiraIssuesUsingJql | Search issues with JQL |
Comments
| Tool | Description |
| ------------------------------------- | -------------------------- |
| mcp_Atlassian_addCommentToJiraIssue | Add a comment to an issue |
| mcp_Atlassian_getJiraIssueComments | Get comments from an issue |
Confluence (if enabled)
| Tool | Description |
| ------------------------------------ | ------------------------ |
| mcp_Atlassian_createConfluencePage | Create a Confluence page |
| mcp_Atlassian_getConfluencePage | Get a Confluence page |
| mcp_Atlassian_searchConfluence | Search Confluence |
Common Patterns
Get Issue Details
Use mcp_Atlassian_getJiraIssue with issueKey: "PROJ-123"
Search for Issues
Use mcp_Atlassian_searchJiraIssuesUsingJql with:
jql: "project = YOUR_PROJECT AND component = 'YOUR_COMPONENT' AND status = 'In Progress'"
Create an Issue
Use mcp_Atlassian_createJiraIssue with:
project: "YOUR_PROJECT"
issueType: "Story"
summary: "Implement new feature"
description: "Description of the feature"
components: ["YOUR_COMPONENT"]
Transition Issue Status
Use mcp_Atlassian_transitionJiraIssue with:
issueKey: "PROJ-123"
transition: "In Progress"
Add Comment
Use mcp_Atlassian_addCommentToJiraIssue with:
issueKey: "PROJ-123"
comment: "Started working on this issue"
JQL Quick Reference
Common JQL queries for the Orient Task Force:
# All issues for YOUR_COMPONENT
project = YOUR_PROJECT AND component = "YOUR_COMPONENT"
# In Progress issues
project = YOUR_PROJECT AND component = "YOUR_COMPONENT" AND status = "In Progress"
# Blockers
project = YOUR_PROJECT AND component = "YOUR_COMPONENT" AND (priority = Blocker OR labels = blocked)
# Recent issues (last 7 days)
project = YOUR_PROJECT AND component = "YOUR_COMPONENT" AND created >= -7d
# My issues
project = YOUR_PROJECT AND component = "YOUR_COMPONENT" AND assignee = currentUser()
# Sprint issues
project = YOUR_PROJECT AND component = "YOUR_COMPONENT" AND sprint in openSprints()
Troubleshooting
"Tool not found" Error
Make sure the Atlassian MCP Server is enabled in your IDE settings. The tools won't appear until the server is connected.
Authentication Issues
The Atlassian MCP Server uses OAuth. If you're not authenticated:
- The tool will prompt you to authenticate
- Follow the OAuth flow in your browser
- Grant the necessary permissions
Rate Limits
The Atlassian MCP Server is subject to Atlassian's rate limits. If you hit limits:
- Reduce query frequency
- Use more specific JQL to reduce result sets
- Cache results when appropriate
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/atlassian-mcp-server-for-jira-mm5t89tz/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/atlassian-mcp-server-for-jira-mm5t89tz' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/atlassian-mcp-server-for-jira-mm5t89tz/download' --output '.skill-downloads/atlassian-mcp-server-for-jira-mm5t89tz/SKILL.md.part' && mv '.skill-downloads/atlassian-mcp-server-for-jira-mm5t89tz/SKILL.md.part' '.skill-downloads/atlassian-mcp-server-for-jira-mm5t89tz/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Original excerpt: Setup
In Cursor
The Atlassian MCP Server is already configured globally. To enable it:
- Open Cursor Settings
- Go to Tools & MCP
- Enable "Atlassian-MCP-Server"
Configuration location: ~/.cursor/mcp.json
{
"mcpServers": {
"Atlassian-MCP-Server": {
"url": "https://mcp.atlassian.com/v1/sse"
}
}
}
In Claude Code
Add to your Claude Code MCP settings:
{
"mcpServers": {
"Atlassian-MCP-Server": {
"url": "https://mcp.atlassian.com/v1/sse"
}
}
}
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/atlassian-mcp-server-for-jira-mm5t89tz/SKILL.md' && test -s '.skill-downloads/atlassian-mcp-server-for-jira-mm5t89tz/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/atlassian-mcp' && cp -R '.skill-downloads/atlassian-mcp-server-for-jira-mm5t89tz' '.claude/skills/atlassian-mcp'Cursor
test -f '.skill-downloads/atlassian-mcp-server-for-jira-mm5t89tz/SKILL.md' && test -s '.skill-downloads/atlassian-mcp-server-for-jira-mm5t89tz/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/atlassian-mcp' && cp -R '.skill-downloads/atlassian-mcp-server-for-jira-mm5t89tz' '.cursor/skills/atlassian-mcp'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/atlassian-mcp-server-for-jira-mm5t89tz'openskills read 'atlassian-mcp-server-for-jira-mm5t89tz'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/atlassian-mcp-server-for-jira-mm5t89tz/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.