Search Jira issues using natural language keywords or raw JQL. Returns issue keys, summaries, statuses, and assignees.

Read raw details of a Jira issue (description, subtasks, changelog, labels, priority, parent, attachments). Data-only — does NOT guide analysis or post comments. Use jira_analyze_task when you need the full investigation workflow.

Download an attachment from a Jira issue. Text files (txt, md, json, log) are returned inline. CSV, XLS, XLSX, PDF are parsed by Python and returned as structured text. Images and other binary files are returned as base64.

Download all attachments from a Jira issue in a single call. Optionally filter by MIME type (e.g. "image/" for images only). Returns all files with their content inline. Use this instead of multiple jira_download_attachment calls.

List Jira issues assigned to the currently authenticated user, optionally filtered by status.

Map a Jira project key to a local repository path. This enables jira_read_task to include the local path hint for code exploration.

Get the local repository path mapped to a Jira project key.

Post a comment on a Jira issue. Returns the comment URL so you can verify it directly.

Edit an existing Jira comment. In manual mode, returns a preview first and requires confirm_token to apply the update.

Full investigation and fix workflow for a Jira issue. Accepts an issue key (AT-123) or full browse URL. Reads the issue, prior comments, linked issues, and attachments; detects duplicate analysis (idempotency); selects a type-aware template (Bug/Story/Task); and provides step-by-step SOP: explore code → plan → baseline test → implement → build verify → post analysis comment. Use this instead of jira_read_task when you want to drive the full workflow end-to-end.