atlassian-mcp

Load detailed guidance based on context: Note: Always load JIRA_API_TOKEN and CONFLUENCE_API_TOKEN from environment variables or a secrets manager — never hardcode credentials. When implementing Atlassian MCP features, provide: - 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 - 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=1 before 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 - Respect user permissions and workspace access controls - Validate JQL/CQL queries before execution (use maxResults=1 probe first) - Handle rate limits with exponential backoff - Use pagination for large result sets (50-100 items per page) - Implement error recovery for network...