All servers / Observability / Kibana MCP server
Kibana MCP server
Kibana MCP Server
Tested by ConnectATDScore 90 out of 100. Tested 2026-11-18 on package version 0.11.1. Package: @tocharianou/mcp-server-kibana · source
Score breakdown
| Runs | 18 / 20 | |
|---|---|---|
| Tool descriptions | 20 / 20 | |
| Package safety | 20 / 20 | |
| Maintenance | 20 / 20 | |
| Adoption | 12 / 20 |
What we saw
- Starts and answers the MCP handshake: yes (6.7 seconds including download)
- Tools offered: 17
- Last published: 2026-10-11
- Weekly downloads (npm): 3,033
- License: Apache-2.0 · Direct dependencies: 11
Want this server set up for your team?
ConnectATD builds AI automation and wires up MCP servers like this one. Tell us what you are trying to do.
Talk to ConnectATDTools and how they are described
Agents choose tools from these descriptions. Under each name you can see how many of its parameters are explained.
get_status1 of 1 parameter describedGet Kibana server status with multi-space support
execute_kb_api2 of 6 parameters describedExecute a custom API request for Kibana with multi-space support. For Elasticsearch document or log searches, use search_elasticsearch instead. Do not use /api/console/proxy for Elasticsearch searches: that Console endpoint can require Dev Tools privileges even when the configured user can read the target indices. Do not use this generic tool to rediscover an Elasticsearch search route when search_elasticsearch already provides the supported workflow. RETRY SAFETY: this tool can reach any write endpoint. A POST retried after a timeout or dropped response can create a duplicate — prefer a caller-chosen stable id (or the vl_* tool for that object type, which documents the safe pattern) over letting the server auto-generate one.
search_kibana_api_paths1 of 1 parameter describedSearch documented Kibana OpenAPI endpoints by keyword. This index does not necessarily contain Kibana internal routes. Do not use this tool to discover how to search Elasticsearch documents or logs; use search_elasticsearch for that.
list_all_kibana_api_pathsno parametersList all Kibana API endpoints as a resource list
get_kibana_api_detail3 of 3 parameters describedGet details for a specific Kibana API endpoint
get_available_spaces1 of 1 parameter describedGet all available Kibana spaces with current context
vl_search_saved_objects16 of 16 parameters describedSearch for Kibana saved objects using Elasticsearch query syntax. This is a universal tool that can search across all saved object types (dashboard, visualization, index-pattern, search, config, lens, map, tag, canvas-workpad, canvas-element, etc.). IMPORTANT: You must specify the 'types' parameter - it is required by the Kibana API. PERFORMANCE TIPS: Always use 'fields' parameter to specify only needed fields (e.g., ['title', 'description']) for faster responses. Use 'perPage' 5-20 for optimal speed. PAGINATION: To get all results, make multiple requests with incrementing 'page' numbers (page=1, page=2, etc.) until you receive fewer results than 'perPage'. Don't stop at the first page - iterate through all pages for complete data. Returns formatted saved object information including type, title, description, and timestamps.
vl_get_saved_object5 of 5 parameters describedGet a single Kibana saved object by type and ID. This is a universal tool that can retrieve any type of saved object (dashboard, visualization, index-pattern, search, config, lens, map, tag, canvas-workpad, canvas-element, etc.) by its exact type and ID. Use this when you know the specific object you want to retrieve. PERFORMANCE: This is much faster than searching when you have the exact type and ID.
vl_bulk_delete_saved_objects3 of 3 parameters describedBulk delete multiple Kibana saved objects by type and ID. This is a destructive operation that permanently removes saved objects (dashboard, visualization, index-pattern, search, config, lens, map, tag, canvas-workpad, canvas-element, etc.). WARNING: Deleted objects cannot be recovered. Use with caution. IMPORTANT: Objects that exist in multiple namespaces require the 'force' parameter to be deleted.
vl_create_saved_object7 of 7 parameters describedCreate a new Kibana saved object (dashboard, visualization, index-pattern, search, config, lens, map, tag, canvas-workpad, canvas-element, etc.). This is a universal tool that can create any type of saved object by specifying the type and attributes. Each object type has specific attribute requirements. IMPORTANT: The 'title' field is required for most object types. Complex fields like panelsJSON, visState should be JSON strings.
vl_update_saved_object7 of 7 parameters describedUpdate a single Kibana saved object by type and ID. This performs a partial update - only the specified attributes will be changed, other attributes remain unchanged. Supports all saved object types (dashboard, visualization, index-pattern, search, config, lens, map, tag, canvas-workpad, canvas-element, etc.). IMPORTANT: Use version parameter for optimistic concurrency control to prevent conflicts.
vl_bulk_update_saved_objects2 of 2 parameters describedUpdate multiple Kibana saved objects in a single operation. Each object can be of different types and will be partially updated (only specified attributes changed). Supports all saved object types (dashboard, visualization, index-pattern, search, config, lens, map, tag, canvas-workpad, canvas-element, etc.). PERFORMANCE: More efficient than multiple single updates. Each object can have individual version control.
analyze_object_dependencies4 of 4 parameters describedAnalyze dependency tree for a Kibana saved object (Dashboard, Visualization, etc.)
analyze_deletion_impact3 of 3 parameters describedAnalyze the impact of deleting or modifying a saved object (what will be affected)
check_dashboard_health3 of 3 parameters describedPerform health check on a Dashboard to detect broken references, performance issues, etc.
scan_all_dashboards_health2 of 2 parameters describedScan health status of all Dashboards in a space (returns summary report)
search_elasticsearch4 of 4 parameters describedSearch Elasticsearch documents, logs, and aggregations through Kibana using Elasticsearch Query DSL. USE THIS TOOL whenever the task is to find or inspect Elasticsearch data. Do not first search Kibana API paths and do not call /api/console/proxy through execute_kb_api for Elasticsearch searches. The Console proxy can require the Kibana Dev Tools privilege even when the configured user is allowed to read the target indices. This tool uses the user's existing Elasticsearch permissions. SEARCH STRATEGY FOR LOGS: 1. Start with the narrowest known index pattern and a small time window. 2. Set size explicitly (usually 10-50; maximum 100). 3. Request only useful _source fields when exploring high-volume logs. 4. Sort by the timestamp field if chronology matters. 5. After finding a trace/correlation id, narrow follow-up searches to that id and a small surrounding time window. 6. Prefer exact term/keyword filters when the field mapping supports them; use match/query_string only when text analysis is intended. The body is Elasticsearch Query DSL, not Kibana KQL. If the user describes a filter in KQL terms, translate the intent to Query DSL before calling the tool. A wildcard-only index segment ('*', '**', '_all'), an empty body, and body.size > 100 are rejected. Avoid broad match_all searches. Aggregations are supported through the same body. The returned hits preserve the original _source, including dynamic/custom properties. This uses Kibana's internal /internal/search/es endpoint, so its contract can change between Kibana versions.
Tested in a sandbox with an empty environment: no API keys, a throwaway folder, nothing from a real account. A passing test shows the server runs and responds. It is not a security audit.