Bragproof

← Reports

@tocharianou/mcp-server-kibana

Starts with no setup0.11.1npm

Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.

Needs to start: nothing
Returns a result when called with no setup: 0 of 2 tools tried
Contacts while installing and starting: nothing

17tools listed
0hosts contacted
0files written
0.3 sto start
162dependencies

What it contacted

Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.

Starting it

npx -y @tocharianou/mcp-server-kibana@0.11.1

Installing a package runs its code. Use a sandbox for anything you have not read.

Calling its tools

2 tools that take no input and look read-only were called once with nothing. 0 returned a result.

get_statusNo usable answer tool reported an error: Error: GET request failed: connect ECONNREFUSED 127.0.0.1:5601
get_available_spacesNo usable answer tool reported an error: Error: GET request failed: connect ECONNREFUSED 127.0.0.1:5601

During the calls it contacted nothing it had not already contacted.

Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.

What its tools tell an agent

In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.

4 tools with commands in capitals or very long text
  • Gives the agent orders in vl_search_saved_objects: fig, lens, map, tag, canvas-workpad, canvas-element, etc.). IMPORTANT: You must specify the 'types' parameter - it is required by the Kibana API. PERFORMANCE TIPS: Alway
  • Gives the agent orders in vl_bulk_delete_saved_objects: ING: Deleted objects cannot be recovered. Use with caution. IMPORTANT: Objects that exist in multiple namespaces require the 'force' parameter to be deleted.
  • Gives the agent orders in vl_create_saved_object: utes. Each object type has specific attribute requirements. IMPORTANT: The 'title' field is required for most object types. Complex fields like panelsJSON, visState shou
  • Gives the agent orders in vl_update_saved_object: fig, lens, map, tag, canvas-workpad, canvas-element, etc.). IMPORTANT: Use version parameter for optimistic concurrency control to prevent conflicts.

Common and usually harmless: it is how many makers stress how a tool should be used.

Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.

Tools

get_status space
Get Kibana server status with multi-space support
execute_kb_api method, path, body, params, space, break_token_rule
Execute 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_paths search
Search 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_paths
List all Kibana API endpoints as a resource list
get_kibana_api_detail method, path, raw
Get details for a specific Kibana API endpoint
12 more tools
get_available_spaces include_details
Get all available Kibana spaces with current context
vl_search_saved_objects search, types, perPage, page, fields, filter, sortField, sortOrder, defaultSearchOperator, hasReference, hasNoReference, hasReferenceOperator, hasNoReferenceOperator, aggs, space, break_token_rule
Search 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_object type, id, useResolve, space, break_token_rule
Get 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_objects objects, force, space
Bulk 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_object type, attributes, id, overwrite, references, initialNamespaces, space
Create 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_object type, id, attributes, references, version, upsert, space
Update 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_objects objects, space
Update 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_dependencies id, type, space, max_depth
Analyze dependency tree for a Kibana saved object (Dashboard, Visualization, etc.)
analyze_deletion_impact id, type, space
Analyze the impact of deleting or modifying a saved object (what will be affected)
check_dashboard_health dashboard_id, space, check_indices
Perform health check on a Dashboard to detect broken references, performance issues, etc.
scan_all_dashboards_health space, max_dashboards
Scan health status of all Dashboards in a space (returns summary report)
search_elasticsearch index, body, space, break_token_rule
Search 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.

Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.

Install facts

LicenseApache-2.0
Needsnode >=18
Sourcegithub.com/TocharianOU/mcp-server-kibana
Install scriptsNone declared by it or anything installed with it.
Tarballsha512-xAmtdUh+yMFzkP/OtbwDprqgsey9wk5ATMNVwmZHbXVayb5nQNyYSIzJtWcI8pwlEcnNjFBbU+BbpyCiRI7wRQ==

Check this report yourself

This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.

Show it on your README

Bragproof: Starts with no setup

[![Bragproof](https://bragproof.smaverk.com/badge/@tocharianou/mcp-server-kibana.svg)](https://bragproof.smaverk.com/r/%40tocharianou/mcp-server-kibana)

New version out? Ask for a fresh report.