atlassian-mcp
jeffallan/claude-skills
Integrate Jira and Confluence via MCP protocol for issue tracking, documentation, and sprint management.
What is atlassian-mcp?
This skill enables querying and managing Atlassian products (Jira, Confluence) through the MCP protocol. Use it when you need to search issues with JQL filters, create or update tickets, manage sprints, search or edit Confluence pages with CQL, or automate documentation workflows.
- Query Jira issues with JQL filters and retrieve results with pagination
- Create, update, and link Jira tickets with custom fields
- Search and edit Confluence pages using CQL syntax
- Manage sprints, backlogs, and boards
- Configure MCP server authentication with OAuth 2.0 and API tokens
- Sync meeting notes and documentation between systems
How to install atlassian-mcp
npx skills add https://github.com/jeffallan/claude-skills --skill atlassian-mcp- MCP server installed (official cloud, open-source, or self-hosted)
- Jira and/or Confluence instance with API access
- API token or OAuth 2.0 credentials for authentication
- Environment variables configured for JIRA_URL, JIRA_EMAIL, JIRA_API_TOKEN, CONFLUENCE_URL, CONFLUENCE_EMAIL, CONFLUENCE_API_TOKEN
How to use atlassian-mcp
- 1.Select and configure an MCP server (official, open-source, or self-hosted)
- 2.Set up authentication credentials as environment variables (never hardcode tokens)
- 3.Write and validate JQL queries for Jira or CQL queries for Confluence using maxResults=1 probe first
- 4.Implement tool calls with pagination (50-100 items per page) and error handling
- 5.Verify required permission scopes with read-only operations before write or bulk operations
- 6.Deploy and monitor rate limits with exponential backoff
Use cases
- Retrieve open issues assigned to a user in the current sprint
- Search Confluence pages for deployment runbooks or documentation
- Automate issue triage by querying bugs created in the last 7 days
- Sync meeting notes to Jira tickets with custom fields
- Generate documentation reports from issue data across projects
- Project managers automating Jira workflows
- Engineers integrating Atlassian tools into CI/CD pipelines
- Technical writers syncing documentation between Confluence and other systems
- DevOps teams managing sprint backlogs and issue tracking
atlassian-mcp FAQ
Official cloud servers are maintained by Atlassian and integrate directly with cloud instances. Open-source servers like @sooperset/mcp-atlassian offer flexibility for self-hosted or custom setups but require manual maintenance and configuration.
Always load API tokens from environment variables or a secrets manager. Never hardcode credentials in configuration files or code. Use ${VARIABLE_NAME} syntax in JSON configs to reference environment variables.
Always test with maxResults=1 first to validate the query syntax and confirm it returns expected results. This prevents accidental large data transfers and helps identify permission issues early.
Implement exponential backoff when rate limit headers are received. Use pagination with 50-100 items per page for large result sets. Log API calls to monitor usage patterns.
Yes, you can query Jira issues and sync data to Confluence pages in the same workflow. Ensure both JIRA_API_TOKEN and CONFLUENCE_API_TOKEN are configured, and test permissions for both services separately first.
Full instructions (SKILL.md)
Source of truth, from jeffallan/claude-skills.
name: atlassian-mcp description: Integrates with Atlassian products to manage project tracking and documentation via MCP protocol. Use when querying Jira issues with JQL filters, creating and updating tickets with custom fields, searching or editing Confluence pages with CQL, managing sprints and backlogs, setting up MCP server authentication, syncing documentation, or debugging Atlassian API integrations. license: MIT metadata: author: https://github.com/Jeffallan version: "1.1.0" domain: platform triggers: Jira, Confluence, Atlassian, MCP, tickets, issues, wiki, JQL, CQL, sprint, backlog, project management role: expert scope: implementation output-format: code related-skills: mcp-developer, api-designer, security-reviewer
Atlassian MCP Expert
When to Use This Skill
- Querying Jira issues with JQL filters
- Searching or creating Confluence pages
- Automating sprint workflows and backlog management
- Setting up MCP server authentication (OAuth/API tokens)
- Syncing meeting notes to Jira tickets
- Generating documentation from issue data
- Debugging Atlassian API integration issues
- Choosing between official vs open-source MCP servers
Core Workflow
- Select server - Choose official cloud, open-source, or self-hosted MCP server
- Authenticate - Configure OAuth 2.1, API tokens, or PAT credentials
- Design queries - Write JQL for Jira, CQL for Confluence; validate with
maxResults=1before full execution - Implement workflow - Build tool calls, handle pagination, error recovery
- Verify permissions - Confirm required scopes with a read-only probe before any write or bulk operation
- Deploy - Configure IDE integration, test permissions, monitor rate limits
Reference Guide
Load detailed guidance based on context:
| Topic | Reference | Load When |
|---|---|---|
| Server Setup | references/mcp-server-setup.md | Installation, choosing servers, configuration |
| Jira Operations | references/jira-queries.md | JQL syntax, issue CRUD, sprints, boards, issue linking |
| Confluence Ops | references/confluence-operations.md | CQL search, page creation, spaces, comments |
| Authentication | references/authentication-patterns.md | OAuth 2.0, API tokens, permission scopes |
| Common Workflows | references/common-workflows.md | Issue triage, doc sync, sprint automation |
Quick-Start Examples
JQL Query Samples
# Open issues assigned to current user in a sprint
project = PROJ AND status = "In Progress" AND assignee = currentUser() ORDER BY priority DESC
# Unresolved bugs created in the last 7 days
project = PROJ AND issuetype = Bug AND status != Done AND created >= -7d ORDER BY created DESC
# Validate before bulk: test with maxResults=1 first
project = PROJ AND sprint in openSprints() AND status = Open ORDER BY created DESC
CQL Query Samples
# Find pages updated in a specific space recently
space = "ENG" AND type = page AND lastModified >= "2024-01-01" ORDER BY lastModified DESC
# Search page text for a keyword
space = "ENG" AND type = page AND text ~ "deployment runbook"
Minimal MCP Server Configuration
{
"mcpServers": {
"atlassian": {
"command": "npx",
"args": ["-y", "@sooperset/mcp-atlassian"],
"env": {
"JIRA_URL": "https://your-domain.atlassian.net",
"JIRA_EMAIL": "user@example.com",
"JIRA_API_TOKEN": "${JIRA_API_TOKEN}",
"CONFLUENCE_URL": "https://your-domain.atlassian.net/wiki",
"CONFLUENCE_EMAIL": "user@example.com",
"CONFLUENCE_API_TOKEN": "${CONFLUENCE_API_TOKEN}"
}
}
}
}
Note: Always load
JIRA_API_TOKENandCONFLUENCE_API_TOKENfrom environment variables or a secrets manager — never hardcode credentials.
Constraints
MUST DO
- Respect user permissions and workspace access controls
- Validate JQL/CQL queries before execution (use
maxResults=1probe first) - Handle rate limits with exponential backoff
- Use pagination for large result sets (50-100 items per page)
- Implement error recovery for network failures
- Log API calls for debugging and audit trails
- Test with read-only operations first
- Document required permission scopes
- Confirm before any write or bulk operation against production data
MUST NOT DO
- Hardcode API tokens or OAuth secrets in code
- Ignore rate limit headers from Atlassian APIs
- Create issues without validating required fields
- Skip input sanitization on user-provided query strings
- Deploy without testing permission boundaries
- Update production data without confirmation prompts
- Mix different authentication methods in same session
- Expose sensitive issue data in logs or error messages
Output Templates
When implementing Atlassian MCP features, provide:
- MCP server configuration (JSON/environment vars)
- Query examples (JQL/CQL with explanations)
- Tool call implementation with error handling
- Authentication setup instructions
- Brief explanation of permission requirements
Related skills
More from jeffallan/claude-skills and the wider catalog.

chaos-engineer
Design chaos experiments, failure injection frameworks, and game day exercises for resilient distributed systems.

cli-developer
Build production CLI tools with argument parsing, completions, and interactive prompts across Node.js, Python, and Go.

cloud-architect
Design cloud architectures, migration plans, cost optimization, and disaster recovery across AWS, Azure, and GCP.

code-documenter
Generate and validate technical documentation—docstrings, API specs, JSDoc, and developer guides.

code-reviewer
Analyze code diffs for bugs, security vulnerabilities, and architectural concerns with prioritized, actionable feedback.

cpp-pro
Modern C++20/23 expert for high-performance systems, template metaprogramming, and zero-overhead abstractions.