MCP.so
Sign In

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

16

Get 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.

Comments

Basic information

Category

Other

License

Apache-2.0

Transports

stdio

Author

TocharianOU

More Other MCP servers