Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Kibana

NPM · @TOCHARIANOU/MCP-SERVER-KIBANA · SCANNED SEP 21

Kibana MCP Server with dynamic API discovery and comprehensive Elastic Stack integration

+3 this week 76 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 44 of 142 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability41
  • 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Fail
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 3038 tokens (~168/item across 18 items; 16 tools + 2 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage98
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 94% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "execute_kb_api" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the Kibana MCP server?

Kibana runs locally as an npm package, launched with npx -y @tocharianou/mcp-server-kibana. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @tocharianou/mcp-server-kibana

# add to Claude Code
claude mcp add tocharianou-kibana -- npx -y @tocharianou/mcp-server-kibana
// .cursor/mcp.json
{
  "mcpServers": {
    "tocharianou-kibana": {
      "command": "npx",
      "args": [
        "-y",
        "@tocharianou/mcp-server-kibana"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "tocharianou-kibana": {
      "command": "npx",
      "args": [
        "-y",
        "@tocharianou/mcp-server-kibana"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add tocharianou-kibana -- npx -y @tocharianou/mcp-server-kibana
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "tocharianou-kibana": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@tocharianou/mcp-server-kibana"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add tocharianou-kibana --command npx --arg -y --arg @tocharianou/mcp-server-kibana
# ~/.hermes/config.yaml
mcp_servers:
  tocharianou-kibana:
    command: "npx"
    args: ["-y", "@tocharianou/mcp-server-kibana"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "tocharianou-kibana": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@tocharianou/mcp-server-kibana"
      ]
    }
  }
}
# add to Vellum
assistant mcp add tocharianou-kibana -t stdio -c npx -a -y @tocharianou/mcp-server-kibana
// mcp.json
{
  "mcpServers": {
    "tocharianou-kibana": {
      "command": "npx",
      "args": [
        "-y",
        "@tocharianou/mcp-server-kibana"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Sept 26 0
    • Stability: 0.97 → pass security
    • Security disclosure: unverified → fail functional
  • 20 Sept 26 +1
    • Security disclosure: fail → unverified functional
  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 +15
    • Malware scan: unverified → pass security
  • 16 Sept 26 −14
    • Stability: 0.80 → unverified security
    • Malware scan: pass → unverified security
    • Tool safety: pass → unverified security
    • Capabilities: pass → unverified functional
    • Schema quality: 0 → unverified functional
    • Tool coverage: 100 → unverified functional
    • Package version: 0.10.1 → 0.10.2 functional
  • 15 Sept 26 0
    • Stability: 0.77 → unverified security
    • Tool safety: pass → unverified security
    • Capabilities: pass → unverified functional
    • Schema quality: 0 → unverified functional
    • Tool coverage: 100 → unverified functional
    • Package version: 0.10.0 → 0.10.1 functional
  • 14 Sept 26 −3
    • Security disclosure: unverified → fail functional
    • Stability: pass → 0.77 functional
  • 13 Sept 26 0
    • Stability: 0.97 → pass security
    • Security disclosure: fail → unverified functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Sept 2026 · Analysed npm/@tocharianou/mcp-server-kibana@0.10.2

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 142 packages
Packages resolved 142
Stale 44
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 16 exposed · ~3,022 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
analyze_deletion_impact ~71

Analyze the impact of deleting or modifying a saved object (what will be affected)

NameTypeReqDescription
idstringyesSaved object ID to analyze
spacestringKibana space (optional)
typestringyesSaved object type (e.g., visualization, lens, index-pattern)

No output schema declared.

No examples provided.

analyze_object_dependencies ~86

Analyze dependency tree for a Kibana saved object (Dashboard, Visualization, etc.)

NameTypeReqDescription
idstringyesSaved object ID
max_depthnumberMaximum depth to traverse (default: 5)
spacestringKibana space (optional)
typestringyesSaved object type (e.g., dashboard, visualization, lens, index-pattern)

No output schema declared.

No examples provided.

check_dashboard_health ~68

Perform health check on a Dashboard to detect broken references, performance issues, etc.

NameTypeReqDescription
check_indicesbooleanAlso check if referenced Elasticsearch indices exist (requires additional permissions)
dashboard_idstringyesDashboard ID to check
spacestringKibana space (optional)

No output schema declared.

No examples provided.

execute_kb_api ~158

Execute a custom API request for Kibana with multi-space support. 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.

NameTypeReqDescription
body
break_token_rulebooleanSet to true to bypass token limits in critical situations. Use sparingly to avoid context overflow.
methodstringyes
paramsobject
pathstringyes
spacestringTarget Kibana space (optional, defaults to configured space)

No output schema declared.

No examples provided.

get_available_spaces ~37

Get all available Kibana spaces with current context

NameTypeReqDescription
include_detailsbooleanInclude detailed space information (name, description, etc.)

No output schema declared.

No examples provided.

get_kibana_api_detail ~81

Get details for a specific Kibana API endpoint

NameTypeReqDescription
methodstringyesHTTP method, e.g. GET, POST, PUT, DELETE
pathstringyesAPI path, e.g. /api/actions/connector_types
rawbooleanIf true, return raw JSON schema instead of simplified TypeScript interface

No output schema declared.

No examples provided.

get_status ~36

Get Kibana server status with multi-space support

NameTypeReqDescription
spacestringTarget Kibana space (optional, defaults to configured space)

No output schema declared.

No examples provided.

list_all_kibana_api_paths ~24

List all Kibana API endpoints as a resource list

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

scan_all_dashboards_health ~58

Scan health status of all Dashboards in a space (returns summary report)

NameTypeReqDescription
max_dashboardsnumberMaximum number of dashboards to scan (default: 50)
spacestringKibana space (optional)

No output schema declared.

No examples provided.

search_kibana_api_paths ~33

Search Kibana API endpoints by keyword

NameTypeReqDescription
searchstringyesSearch keyword for filtering API endpoints

No output schema declared.

No examples provided.

vl_bulk_delete_saved_objects ~193

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.

NameTypeReqDescription
forcebooleanForce deletion of objects that exist in multiple namespaces. Set to true if you get an error about objects existing in multiple namespaces. WARNING: This also deletes legacy URL aliases and can place…
objectsarrayyesREQUIRED: Array of objects to delete. Each object must have 'type' and 'id' fields. Minimum 1 object required.
spacestringTarget Kibana space (optional, defaults to configured space)

No output schema declared.

No examples provided.

vl_bulk_update_saved_objects ~143

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.

NameTypeReqDescription
objectsarrayyesREQUIRED: Array of objects to update. Each object must have 'type', 'id', and 'attributes' fields. Minimum 1 object required.
spacestringTarget Kibana space (optional, defaults to configured space)

No output schema declared.

No examples provided.

vl_create_saved_object ~539

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.

NameTypeReqDescription
attributesobjectyesREQUIRED: Object containing the saved object attributes. Structure varies by type. Common fields: 'title' (required for most types), 'description'. Dashboard: 'panelsJSON', 'timeRestore'. Visualizati…
idstringOPTIONAL: Specific ID for the saved object. If not provided, Kibana will auto-generate a unique ID. Use this when you need a predictable ID or when recreating objects. RETRY SAFETY: if this call is r…
initialNamespacesarrayOPTIONAL: Array of initial namespaces for the object. Used for multi-tenant setups. If not specified, object will be created in the default namespace.
overwritebooleanOPTIONAL: Whether to overwrite an existing object with the same ID. Only relevant when 'id' is specified. Default: false. Set to true to replace existing objects.
referencesarrayOPTIONAL: Array of references to other saved objects. Used to link objects together (e.g., dashboard panels referencing visualizations). Each reference needs id, type, and name.
spacestringTarget Kibana space (optional, defaults to configured space)
typeyesREQUIRED: The saved object type. Common types: 'dashboard', 'visualization', 'index-pattern', 'search', 'config', 'lens', 'map', 'tag', 'canvas-workpad', 'canvas-element'. Supports multiple formats b…

No output schema declared.

No examples provided.

vl_get_saved_object ~312

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.

NameTypeReqDescription
break_token_rulebooleanSet to true to bypass token limits in critical situations. Use sparingly to avoid context overflow.
idstringyesREQUIRED: The saved object ID. This is the unique identifier for the specific object you want to retrieve.
spacestringTarget Kibana space (optional, defaults to configured space)
typeyesREQUIRED: The saved object type. Common types: 'dashboard', 'visualization', 'index-pattern', 'search', 'config', 'lens', 'map', 'tag', 'canvas-workpad', 'canvas-element'. Supports multiple formats:…
useResolvebooleanUse resolve API instead of get API. The resolve API can handle legacy URL aliases from object ID migrations. Use this if you're having trouble finding an object that may have had its ID changed durin…

No output schema declared.

No examples provided.

vl_search_saved_objects ~823

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.

NameTypeReqDescription
aggsstringAggregation structure, serialized as a string. Use for advanced analytics on saved objects.
break_token_rulebooleanSet to true to bypass token limits in critical situations. Use sparingly to avoid context overflow.
defaultSearchOperatorstringDefault operator for simple_query_string (OR/AND, default: OR)
fieldsPERFORMANCE OPTIMIZATION: Specify which fields to return in the attributes key. Examples: ['title', 'description'] for basic info, ['title', 'description', 'updated_at'] for metadata. IMPORTANT: Usin…
filterstringKQL string filter (e.g., 'dashboard.attributes.title: "My Dashboard"')
hasNoReferenceFilter to objects that do not have a relationship with the type and identifier combination. Example: {type: 'index-pattern', id: 'my-pattern-id'}
hasNoReferenceOperatorstringOperator for has_no_reference parameter (OR/AND, default: OR)
hasReferenceFilter to objects that have a relationship with the type and ID combination. Example: {type: 'index-pattern', id: 'my-pattern-id'}
hasReferenceOperatorstringOperator for has_reference parameter (OR/AND, default: OR)
pagenumberPage number to return (starts from 1). Use with perPage for pagination. Example: page=1 gets first 20 results, page=2 gets results 21-40, etc. IMPORTANT: To get all results, you need to make multiple…
perPagenumberNumber of saved objects per page (default: 20). PERFORMANCE TIP: Use 5-20 for faster responses. Large values (>50) can be slow and may timeout. Always combine with 'fields' parameter to limit data wh…
searchstringSearch query to filter saved objects. Supports boolean operators (AND, OR), wildcards (*), and phrases in quotes. Example: 'nginx AND logs' or 'web*'.
sortFieldstringField to sort by (e.g., 'updated_at', 'created_at', 'type', 'dashboard.attributes.title')
sortOrderstringSort order: 'asc' for ascending, 'desc' for descending (default: 'desc')
spacestringTarget Kibana space (optional, defaults to configured space)
typesyesREQUIRED: Saved object types to include. Common types: 'dashboard', 'visualization', 'index-pattern', 'search', 'config', 'lens', 'map', 'tag', 'canvas-workpad', 'canvas-element'. Use ['dashboard', '…

No output schema declared.

No examples provided.

vl_update_saved_object ~360

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.

NameTypeReqDescription
attributesobjectyesREQUIRED: Object containing the attributes to update. Only specified attributes will be changed (partial update). Common fields: 'title', 'description'. Type-specific fields: Dashboard: 'panelsJSON',…
idstringyesREQUIRED: The saved object ID. This is the unique identifier for the object you want to update.
referencesarrayOPTIONAL: Array of references to other saved objects. Updates the object's references. Each reference needs id, type, and name.
spacestringTarget Kibana space (optional, defaults to configured space)
typeyesREQUIRED: The saved object type. Common types: 'dashboard', 'visualization', 'index-pattern', 'search', 'config', 'lens', 'map', 'tag', 'canvas-workpad', 'canvas-element'. Supports multiple formats b…
upsertobjectOPTIONAL: Attributes to use if the object doesn't exist (will create object if not found). Useful for create-or-update scenarios.
versionstringOPTIONAL: Version string for optimistic concurrency control. Use this to prevent conflicts when multiple processes update the same object. Get the version from a previous get/search operation.

No output schema declared.

No examples provided.

Common questions

What is the Kibana MCP server?

Kibana is an MCP server listed in the public MCP registry as io.github.TocharianOU/kibana. Kibana MCP Server with dynamic API discovery and comprehensive Elastic Stack integration. This page covers its npm package (@tocharianou/mcp-server-kibana).

Is the Kibana MCP server safe to use?

Kibana scores 76 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Kibana MCP server expose?

Kibana exposes 16 tools: get_status, execute_kb_api, search_kibana_api_paths, list_all_kibana_api_paths, get_kibana_api_detail, and 11 more. Their descriptions and schemas cost roughly 3,022 tokens of context every time the server is loaded.

Is the Kibana MCP server still maintained?

Kibana is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Kibana MCP server under?

Kibana declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.