Model Context Protocol (MCP) server for Kibana integration
This server demonstrates solid definition quality with consistent naming conventions, complete input schemas, and clear descriptions across all 7 tools. All tools follow verb_noun naming patterns (list_*, get_*, export_*, search_*). Descriptions range from 45-89 characters, falling within the productive mid-range (baseline 194 chars average, but for domain-specific tools this is acceptable). Input schemas are present and properly typed for all tools. However, output schemas are not documented, the server provides no schema documentation for what these tools return, which violates the pattern:tool and pattern:response-shaper requirements. Additionally, no error handling guidance is present in descriptions, and parameter descriptions could be more detailed regarding valid ranges and constraints. The read-only nature of all tools is commendable from a security perspective but limits the server's utility for operational automation.
Export a dashboard with all its dependencies (visualizations, data views, etc.)
Get detailed information about a specific dashboard
Get detailed information about a specific visualization
List all Kibana dashboards with optional search filtering
List all data views (index patterns) in Kibana
List all Kibana visualizations
No output schemas documented for any tool. Users and LLMs cannot determine what fields to expect in responses, breaking downstream tool composition and forcing agents to guess field names.
No error handling guidance in tool descriptions. When a dashboard is not found or an Elasticsearch query fails, the descriptions do not tell the LLM what to do next (retry, ask user, search alternatives).
Parameter descriptions for list_* tools do not specify result limits or explain pagination behavior. 'perPage' defaults to 20 with max 100, but descriptions lack guidance on when results are truncated or whether a next_page indicator is returned.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-22 | B | 75 | 2026-07-28+ | v2 |
| 2026-03-09 | D | 51 | - | v1 |
Search Elasticsearch data through Kibana using Elasticsearch query DSL
search_logs 'query' parameter accepts a raw Elasticsearch DSL object but lacks constraint documentation. Description should explain valid query syntax, warn against injection risks, and provide an example format constraint (not example values).
list_data_views has an empty schema properties object, no parameters are documented. While the tool may accept no required parameters, the lack of any documentation makes its function ambiguous.