Kibana MCP Server
by
Provides a Model Context Protocol (MCP) server that enables MCP‑compatible clients to access, search, and manage Kibana APIs using natural language or programmatic requests.
Kibana MCP Server Overview
What is Kibana MCP Server about?
Kibana MCP Server implements an MCP endpoint that wraps the official Elastic Kibana OpenAPI specification. It dynamically exposes every Kibana API as tools and resources, allowing MCP‑compatible clients (e.g., Claude Desktop) to query status, list endpoints, retrieve details, and execute arbitrary Kibana requests.
How to use Kibana MCP Server?
- Installation – Install globally or locally with npm:
npm install -g @tocharian/mcp-server-kibana # or npm install @tocharian/mcp-server-kibana - Run via CLI – Supply required environment variables:
KIBANA_URL=http://localhost:5601 \ KIBANA_USERNAME=admin \ KIBANA_PASSWORD=secret \ npx @tocharian/mcp-server-kibana - Claude Desktop Integration – Add a server entry to
claude_desktop_config.json(MacOS or Windows) using the same env vars. The client will automatically invoke the server’s tools. - Resource Mode – Access raw metadata through URIs such as
kibana-api://paths?search=dashboardorkibana-api://path/GET/%2Fapi%2Fstatus.
Key Features of Kibana MCP Server
- Automatic ingestion of the Elastic Kibana OpenAPI (ES8) to stay in sync with Kibana releases.
- Secure authentication via username/password, with optional TLS/CA support.
- Multi‑space awareness for enterprise Kibana deployments.
- Exposes Kibana endpoints as tools (
get_status,execute_kb_api,search_kibana_api_paths, etc.) and resources (kibana-api://paths,kibana-api://path/...). - Type‑safe TypeScript implementation, easy to extend.
- Compatible with any MCP client; optimized for Claude Desktop’s tool‑based prompting.
Use Cases of Kibana MCP Server
- Operational monitoring – Retrieve cluster health, index status, or dashboard listings via natural‑language queries.
- Automation – Programmatically create, update, or delete saved objects, cases, or spaces as part of CI/CD pipelines.
- Exploratory debugging – Search for specific API endpoints, view request/response schemas, and execute ad‑hoc calls without leaving the chat interface.
- Multi‑tenant management – List and switch between Kibana spaces, enabling per‑team or per‑environment operations.
- Education & onboarding – New users can ask “How do I list all dashboards?” and receive a step‑by‑step execution generated by the server.
FAQ from the Kibana MCP Server
Q: Do I need a specific Kibana version? A: The server uses the OpenAPI spec from Elastic Stack 8.x. It works with any Kibana 8 release that matches the spec.
Q: Can I run the server behind a proxy?
A: Yes. Set KIBANA_URL to the proxy address and configure any required proxy env vars (e.g., HTTPS_PROXY).
Q: Is TLS verification mandatory?
A: By default TLS certificates are validated. For self‑signed certs you can either provide KIBANA_CA_CERT or disable validation with NODE_TLS_REJECT_UNAUTHORIZED=0 (use with caution).
Q: How do I increase request timeout or retries?
A: Adjust KIBANA_TIMEOUT (ms) and KIBANA_MAX_RETRIES environment variables.
Q: What if Claude Desktop does not detect the server? A: Ensure the configuration JSON is valid, restart Claude Desktop, and verify environment variables are correctly set.
Kibana MCP Server's README
Kibana MCP Server
API Specification
This project is based on the official Elastic Kibana API documentation and uses the OpenAPI YAML specification from Elastic Stack 8.x (ES8) to dynamically retrieve and manage all Kibana API endpoints. For the latest details, see the Kibana API documentation.
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.
This project is community-maintained and is not an official product of Elastic or MCP.
🚀 Installation
Quick Install
# Global installation (recommended)
npm install -g @tocharian/mcp-server-kibana
# Or local installation
npm install @tocharian/mcp-server-kibana
Alternative: From Source
git clone https://github.com/TocharinOU/mcp-server-kibana.git
cd mcp-server-kibana
npm install
npm run build
🎯 Quick Start
Method 1: Direct CLI Usage
# Set your Kibana credentials and run
KIBANA_URL=http://your-kibana-server:5601 \
KIBANA_USERNAME=your-username \
KIBANA_PASSWORD=your-password \
npx @tocharian/mcp-server-kibana
Method 2: Claude Desktop Integration (Recommended)
Add to your Claude Desktop configuration file:
Config file locations:
- MacOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"kibana-mcp-server": {
"command": "npx",
"args": ["@tocharian/mcp-server-kibana"],
"env": {
"KIBANA_URL": "http://your-kibana-server:5601",
"KIBANA_USERNAME": "your-username",
"KIBANA_PASSWORD": "your-password",
"KIBANA_DEFAULT_SPACE": "default",
"NODE_TLS_REJECT_UNAUTHORIZED": "0"
}
}
}
}
Method 3: Using Environment File
# Create .env file
cat > kibana-mcp.env << EOF
KIBANA_URL=http://your-kibana-server:5601
KIBANA_USERNAME=your-username
KIBANA_PASSWORD=your-password
NODE_TLS_REJECT_UNAUTHORIZED=0
EOF
# Run with environment file
env $(cat kibana-mcp.env | xargs) npx @tocharian/mcp-server-kibana
Features
- Connect to local or remote Kibana instances
- Secure authentication (username/password)
- SSL/TLS and custom CA certificate support
- Multi-space support for enterprise Kibana environments
- Exposes Kibana API endpoints as both tools and resources
- Search, view, and execute Kibana APIs from MCP clients
- Type-safe, extensible, and easy to integrate
Directory Structure
├── index.ts # Server entry point
├── src/
│ ├── types.ts # Type definitions and schemas
│ ├── base-tools.ts # Tool registration and API logic
│ ├── prompts.ts # Prompt registration (expert & resource helper)
│ └── resources.ts # Resource registration (API paths/URIs)
├── kibana-openapi-source.yaml # Kibana API OpenAPI index
├── README.md # English documentation
├── README_zh.md # Chinese documentation
Resources
| Resource URI | Description |
|---|---|
kibana-api://paths |
Returns all available Kibana API endpoints (can filter with search param) |
kibana-api://path/{method}/{encoded_path} |
Returns details for a specific API endpoint |
Examples:
kibana-api://paths?search=saved_objectskibana-api://path/GET/%2Fapi%2Fstatus
Tools
| Tool Name | Description | Input Parameters |
|---|---|---|
get_status |
Get the current status of the Kibana server | space (optional string) - Target Kibana space |
execute_kb_api |
Execute a custom Kibana API request | method (GET/POST/PUT/DELETE), path (string), body (optional), params (optional), space (optional string) |
get_available_spaces |
Get available Kibana spaces and current context | include_details (optional boolean) - Include full space details |
search_kibana_api_paths |
Search Kibana API endpoints by keyword | search (string) |
list_all_kibana_api_paths |
List all Kibana API endpoints | None |
get_kibana_api_detail |
Get details for a specific Kibana API endpoint | method (string), path (string) |
Prompts
| Prompt Name | Description |
|---|---|
kibana-tool-expert |
Tool expert mode (highly recommended in Claude Desktop), supports intelligent analysis, search, execution, and explanation of Kibana APIs via tools. Recommended for most users. |
kibana-resource-helper |
Resource helper mode, guides how to access and use Kibana API info via resource URIs. Suitable for clients that only support resource access or need raw API metadata. |
Configuration
Configure the server via environment variables:
| Variable Name | Description | Required |
|---|---|---|
KIBANA_URL |
Kibana server address (e.g. http://localhost:5601) | Yes |
KIBANA_USERNAME |
Kibana username | Yes |
KIBANA_PASSWORD |
Kibana password | Yes |
KIBANA_DEFAULT_SPACE |
Default Kibana space (default: 'default') | No |
KIBANA_CA_CERT |
CA certificate path (optional, for SSL verification) | No |
KIBANA_TIMEOUT |
Request timeout in ms (default 30000) | No |
KIBANA_MAX_RETRIES |
Max request retries (default 3) | No |
NODE_TLS_REJECT_UNAUTHORIZED |
Set to 0 to disable SSL certificate validation (use with caution) |
No |
📦 Package Information
- NPM Package: @tocharian/mcp-server-kibana
- GitHub Repository: TocharinOU/mcp-server-kibana
- Node.js: >= 18.0.0
- Package Size: ~685KB (6.4MB unpacked)
🔧 Troubleshooting
Common Issues
"import: command not found" error
# Make sure you're using the latest version
npm install -g @tocharian/mcp-server-kibana@latest
# Or try using node directly
node $(which mcp-server-kibana)
Connection issues
- Verify Kibana URL is accessible
- Check authentication credentials
- For SSL issues, try setting
NODE_TLS_REJECT_UNAUTHORIZED=0
Claude Desktop not detecting the server
- Restart Claude Desktop after config changes
- Check config file syntax with a JSON validator
- Verify environment variables are set correctly
Example Queries
- "What is the status of my Kibana server?"
- "What is the status of my Kibana server in the 'marketing' space?"
- "List all available Kibana spaces I can access."
- "List all available Kibana API endpoints."
- "Show details for the POST /api/saved_objects/_find endpoint."
- "Execute a custom API request for /api/status."
- "Get a list of all dashboards in Kibana."
- "Get a list of all dashboards in the 'production' space."
- "Query API endpoints related to endpoint events."
- "List all case-related API endpoints."
- "Create a new case in Kibana."
- "Create a new dashboard in Kibana."
- "Create a new dashboard in the 'dev-team' space."
Two Prompt Modes in Claude Desktop
When using this server with Claude Desktop, two different prompt interaction modes are supported:
1. Tool-based Prompt Mode
- How it works: Claude Desktop can directly call server tools (such as
get_status,execute_api,search_kibana_api_paths, etc.) to answer your questions or perform actions. - Best for: Users who want a conversational, guided experience. The server will automatically search, execute, and explain Kibana APIs.
- Example: "Show all Kibana API endpoints related to saved objects."
- Testing tip: Select the
kibana-tool-expertprompt in Claude Desktop for integration testing, then start using it.
2. Resource-based Prompt Mode
- How it works: Claude Desktop interacts with the server via resource URIs (such as
kibana-api://pathsorkibana-api://path/GET/%2Fapi%2Fstatus), and the server returns structured data for Claude to parse. - Best for: Advanced users, MCP clients that only support resource access, or programming scenarios needing raw API metadata.
- Example: "Get resource kibana-api://paths?search=dashboard"
Note: The two endpoints in resources (kibana-api://paths and kibana-api://path/{method}/{encoded_path}) have corresponding base tools (list_all_kibana_api_paths, get_kibana_api_detail). This design ensures compatibility with MCP clients that cannot intelligently select multiple resources, making it easier for tools like Claude Desktop to interact with Kibana.
Tip: Most users are recommended to use tool mode for a more natural and powerful experience; resource mode offers maximum flexibility for advanced and compatibility use cases.
Development
Install dependencies:
npm install
Build the server:
npm run build
Auto-rebuild in development mode:
npm run watch
Debugging
Since the MCP server communicates via stdio, debugging can be inconvenient. It is recommended to use MCP Inspector:
npm run inspector
After starting, Inspector will provide a browser-accessible debugging tool URL.
Community
This project is community-maintained. Contributions and feedback are welcome! Please be respectful and inclusive in all communications, and follow the Elastic Community Code of Conduct.
License
This project is licensed under the Apache License 2.0. See the LICENSE file for details.
Troubleshooting
- Check if MCP configuration is correct
- Ensure the Kibana address is accessible
- Verify authentication credentials have sufficient permissions
- If using a custom CA, ensure the certificate path is correct and readable
- If using
NODE_TLS_REJECT_UNAUTHORIZED=0, be aware of security risks - Check error messages output in the terminal
Kibana MCP Server Reviews
Login Required
Please log in to share your review and rating for this MCP.
Actions
Kibana MCP Server's Information
- Author
- TocharianOU
- Category
- Monitoring & Observability
- Language
- TypeScript
- License
- Apache License 2.0
- Version
- v0.1.6
- Stars
- 24
- Updated
- 15 days ago
Configuration
{
"mcpServers": {
"kibana-mcp-server": {
"command": "npx",
"args": [
"@tocharian/mcp-server-kibana"
],
"env": {
"KIBANA_URL": "http://your-kibana-server:5601",
"KIBANA_USERNAME": "your-username",
"KIBANA_PASSWORD": "your-password",
"KIBANA_DEFAULT_SPACE": "default",
"KIBANA_CA_CERT": "<PATH_TO_CA_CERT>",
"KIBANA_TIMEOUT": "30000",
"KIBANA_MAX_RETRIES": "3",
"NODE_TLS_REJECT_UNAUTHORIZED": "0"
}
}
}
}Configure Clients
Similar MCP Servers like Kibana MCP Server
Explore related MCPs that share similar capabilities and solve comparable challenges
Phoenix
Officialby Arize-ai
Open-source AI observability platform enabling tracing, evaluation, dataset versioning, experiment tracking, prompt management, and interactive playground for LLM applications.
Grafana MCP Server
by grafana
Provides programmatic access to a Grafana instance and its surrounding ecosystem through the Model Context Protocol, enabling AI assistants and other clients to query and manipulate dashboards, datasources, alerts, incidents, on‑call schedules, and more.
Dynatrace MCP Server
by dynatrace-oss
Provides a local server that enables real‑time interaction with the Dynatrace observability platform, exposing tools for querying data, retrieving problems, sending Slack notifications, and integrating AI assistance.
VictoriaMetrics MCP Server
by VictoriaMetrics-Community
Provides a Model Context Protocol server exposing read‑only VictoriaMetrics APIs, enabling seamless monitoring, observability, and automation through AI‑driven assistants.
Datadog MCP Server
by GeLi2001
Enables interaction with the Datadog API through a Model Context Protocol server, providing access to monitors, dashboards, metrics, logs, events, and incident data.
JMeter MCP Server
by QAInsights
Execute JMeter test plans through Model Context Protocol clients, capture console output, generate HTML dashboards, and automatically analyze JTL results to surface performance metrics, bottlenecks, and actionable recommendations.
Loki MCP Server
by grafana
Provides a Model Context Protocol (MCP) server that enables AI agents to query Grafana Loki log data via stdin/stdout or Server‑Sent Events, supporting both local binary execution and containerized deployment.
Raygun Mcp Server
by MindscapeHQ
Provides comprehensive access to Raygun's API V3 endpoints for crash reporting and real user monitoring via the Model Context Protocol.
Tempo MCP Server
by grafana
Provides Model Context Protocol endpoints that enable AI assistants to query and analyze distributed tracing data stored in Grafana Tempo, supporting both stdin/stdout communication and an HTTP SSE interface.