MCP Server for Azure Cost Management integration with AI-powered analysis
Server has 6 tools with basic schemas and descriptions, but significant gaps limit production readiness. All tools have descriptions (10-60 chars, mostly adequate) and input schemas with type definitions. However, parameter descriptions are sparse or missing context. No output schemas documented. Error handling is minimal, no recovery guidance or actionable error messages. Tool names follow verb_noun convention (get_*, positive). No tool annotations (readOnlyHint, destructiveHint). Composition is reasonable (single responsibility per tool), but missing pagination support on list-like tools and no documented chaining IDs for downstream calls.
Detect cost anomalies and unusual spending patterns
Retrieve Azure cost data for specified time period and filters
Get cost breakdown by department and team
Generate AI-powered cost optimization recommendations
Identify over-provisioned resources for rightsizing
Analyze resource usage trends and patterns
No output schemas documented. LLMs cannot plan downstream calls or extract required fields without knowing response structure.
Parameter descriptions lack actionable constraints. E.g., 'days' has no min/max bounds; 'threshold' lacks units or valid range; 'utilizationThreshold' missing percentage bounds.
No pagination support on list-returning tools (get_cost_data, get_department_breakdown). Large result sets will blow context window.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 55 | 2026-07-28+ | v2 |
No error handling guidance. Tools lack recovery hints (e.g., 'If subscription not found, call list_subscriptions() first'). No categorization of retryable vs fatal errors.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). All tools are read-only but this is not declared in schema, forcing LLMs to infer safety.