Kibana MCP Server
@TocharianOU
About Kibana MCP Server
MCP server for Kibana, Access search and manage Kibana in MCP Client.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-server-kibana": {
"command": "npx",
"args": [
"@tocharianou/mcp-server-kibana"
]
}
}
}Tools
16Get Kibana server status with multi-space support
Execute a custom API request for Kibana with multi-space support
Search Kibana API endpoints by keyword
List all Kibana API endpoints as a resource list
Get details for a specific Kibana API endpoint
Get all available Kibana spaces with current context
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.
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.
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.
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.
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.
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 dependency tree for a Kibana saved object (Dashboard, Visualization, etc.)
Analyze the impact of deleting or modifying a saved object (what will be affected)
Perform health check on a Dashboard to detect broken references, performance issues, etc.
Scan health status of all Dashboards in a space (returns summary report)
Overview
What is Kibana MCP Server?
A Kibana MCP server implementation that allows any MCP-compatible client (such as Claude Desktop) to access your Kibana instance via natural language or programmatic requests. It is community-maintained and not an official Elastic product.
How to use Kibana MCP Server?
Install globally (npm install -g @tocharianou/mcp-server-kibana) or run with npx. Configure environment variables: KIBANA_URL (required) plus one of KIBANA_API_KEY, KIBANA_USERNAME+KIBANA_PASSWORD, or KIBANA_COOKIES. Integrate with Claude Desktop by adding the server configuration to the desktop config file, or run directly from the CLI. Optional variables include KIBANA_DEFAULT_SPACE, KIBANA_CA_CERT, KIBANA_TIMEOUT, MCP_TRANSPORT, MCP_HTTP_PORT, MCP_HTTP_HOST, and NODE_TLS_REJECT_UNAUTHORIZED.
Key features of Kibana MCP Server
- Dual transport modes: Stdio and HTTP
- Multiple authentication methods: API Key, Basic Auth, Cookie
- Multi-space support for enterprise Kibana environments
- SSL/TLS support with custom CA certificates
- Complete saved objects CRUD operations and bulk actions
- Analysis tools for object dependencies and dashboard health
Use cases of Kibana MCP Server
- Perform Kibana server status checks and list available spaces via natural language
- Search, create, update, and delete dashboards, visualizations, and other saved objects
- Analyze saved object dependencies and check deletion impact before removal
- Batch scan all dashboards for health issues
FAQ from Kibana MCP Server
What authentication methods are supported?
API Key (base64 encoded), Basic Auth (username + password), and Cookie-based session authentication are supported, with API Key having highest priority.
How do I integrate this server with Claude Desktop?
Add a "kibana" entry to the mcpServers object in your Claude Desktop configuration file, specifying the npx command, the package name, and the required environment variables (KIBANA_URL and authentication).
Can I run the server over HTTP for remote access?
Yes, set MCP_TRANSPORT=http and optionally configure MCP_HTTP_PORT (default 3000) and MCP_HTTP_HOST. The server will expose endpoints at http://<host>:<port>/mcp and http://<host>:<port>/health.
Is this an official Elastic product?
No, this is a community-maintained project based on the official Elastic Kibana API documentation. It is not an official product of Elastic or MCP.
What Node.js version is required?
Node.js >= 18.0.0 is required to run the Kibana MCP Server.
Frequently asked questions
What authentication methods are supported?
API Key (base64 encoded), Basic Auth (username + password), and Cookie-based session authentication are supported, with API Key having highest priority.
How do I integrate this server with Claude Desktop?
Add a "kibana" entry to the `mcpServers` object in your Claude Desktop configuration file, specifying the `npx` command, the package name, and the required environment variables (KIBANA_URL and authentication).
Can I run the server over HTTP for remote access?
Yes, set `MCP_TRANSPORT=http` and optionally configure `MCP_HTTP_PORT` (default 3000) and `MCP_HTTP_HOST`. The server will expose endpoints at `http://<host>:<port>/mcp` and `http://<host>:<port>/health`.
Is this an official Elastic product?
No, this is a community-maintained project based on the official Elastic Kibana API documentation. It is not an official product of Elastic or MCP.
What Node.js version is required?
Node.js >= 18.0.0 is required to run the Kibana MCP Server.
Basic information
More Other MCP servers
Inbox Zero AI
elie222The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.
Activepieces
activepiecesAI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Mcp
browsermcpBrowser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser

Sequential Thinking
modelcontextprotocolModel Context Protocol Servers

Glasswarp
GlasswarpSee and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
Comments