MCP Server for Jira Analytics providing project data retrieval, issue searching, sprint management, and team workload analysis
The server defines 6 tools with basic structure and all required fields present. However, multiple critical gaps limit production readiness: (1) Tool descriptions are present but lack context about prerequisites, dependencies, and when to use each tool vs. alternatives. (2) Parameter schemas are defined but descriptions are minimal, e.g., 'JQL query string' for get_issues_by_jql does not explain what JQL is, what syntax is valid, or common patterns. (3) Output schemas are completely undocumented, callers have no visibility into response structure, field types, or pagination behavior. (4) Error handling is absent, no guidance on retryability, user-fixable vs. fatal errors, or recovery paths. (5) Tool naming is acceptable (verb_noun pattern) but lacks clarity in distinguishing analytics tools. Overall, definitions are structurally sound but semantically sparse.
Get the changelog (transition history) for a specific Jira issue
Search Jira issues using JQL (Jira Query Language)
Retrieve all Jira projects with metadata including lead and description
Get sprint details including issues, velocity, and burndown data
Calculate status transition durations for issues in a project
Get workload statistics for team members in a project
No output/return schemas documented for any tool. LLMs cannot plan downstream calls, extract fields, or handle pagination without knowing response structure.
Parameter descriptions are minimal and lack actionable constraints. Example: 'JQL query string' does not explain JQL syntax, valid operators, or examples. 'Max results to return (default 50)' lacks min/max bounds or pagination guidance.
No error handling guidance. Tools do not document what errors are retryable, what are user-fixable (e.g., invalid JQL), or what are fatal. LLMs receive raw failures with no recovery path.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-22 | D | 54 | <=2025-11-25 | v2 |
| 2026-03-09 | F | 10 | - | v1 |
Tool descriptions lack context about when to use each tool. E.g., distinction between get_issues_by_jql (general search) and get_transition_times (analytics on status transitions) is unclear. No guidance on dependencies or prerequisite calls.
Pagination not addressed. get_issues_by_jql accepts 'maxResults' and 'startAt' but no description of total available results or next_cursor. LLMs cannot reliably iterate large result sets.
Optional parameters (maxResults, startAt, state, maxIssues) lack clarity on defaults and side effects. 'maxResults default 50' is stated but not enforced in schema (no default keyword). No minimum/maximum constraints.
No validation of Jira API credentials or connection status. Tools assume jiraClient is authenticated and reachable. Failure modes are implicit.