Kibana
Enables AI assistants to interact with Kibana dashboards, visualizations, and Elasticsearch data through read-only resources and executable tools for searching logs, exporting dashboards, and querying data.
What is Kibana?
Kibana is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables ai assistants to interact with kibana dashboards, visualizations, and elasticsearch data through read-only resources and executable tools for searching logs, exporting dashboards, and querying...
Enables AI assistants to interact with Kibana dashboards, visualizations, and Elasticsearch data through read-only resources and executable tools for searching logs, exporting dashboards, and querying data.
This server falls under the Monitoring & Observability and Search & Data Extraction categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Enables AI assistants to interact with Kibana dashboards, vi
Use Cases
Maintainer
Works with
Installation
NPM
npx -y @tocharianou/mcp-server-kibanaManual Installation
npx -y @tocharianou/mcp-server-kibanaConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Kibana
The Kibana MCP Server bridges AI assistants to your Kibana and Elasticsearch stack, exposing read and write capabilities for dashboards, visualizations, saved objects, and raw Elasticsearch queries through natural language. It supports API key, basic auth, and cookie-based authentication so it can connect to both on-prem and Elastic Cloud deployments. Teams use it to investigate incidents, analyze log data, and manage Kibana assets without leaving their AI chat interface.
Prerequisites
- Node.js 18.0.0 or later installed
- A running Kibana instance (local or Elastic Cloud) with network access from your machine
- A Kibana API key, or username/password credentials with appropriate permissions
- An MCP-compatible client such as Claude Desktop or Cursor
Verify Kibana connectivity
Confirm your Kibana instance is reachable and note the base URL (e.g. http://localhost:5601 or https://your-cloud-id.kb.us-east-1.aws.elastic-cloud.com).
curl http://localhost:5601/api/statusObtain authentication credentials
In Kibana, navigate to Stack Management > API Keys and create a key with the necessary privileges. Alternatively, note an existing username and password. The server prioritizes API key over basic auth over session cookies.
Add the server to your MCP client configuration
Edit claude_desktop_config.json and add the Kibana MCP server block, supplying your Kibana URL and chosen authentication method.
{
"mcpServers": {
"kibana": {
"command": "npx",
"args": ["-y", "@tocharianou/mcp-server-kibana"],
"env": {
"KIBANA_URL": "http://localhost:5601",
"KIBANA_API_KEY": "your_encoded_api_key",
"KIBANA_DEFAULT_SPACE": "default"
}
}
}
}Restart your MCP client
Restart Claude Desktop (or your IDE) so it starts the Kibana MCP server process and registers the available tools.
Verify the connection
Ask the assistant to get the Kibana status. This calls the get_status tool and confirms the server can reach your Kibana instance.
Kibana Examples
Client configuration
Minimal Claude Desktop configuration using API key authentication. For basic auth, replace KIBANA_API_KEY with KIBANA_USERNAME and KIBANA_PASSWORD.
{
"mcpServers": {
"kibana": {
"command": "npx",
"args": ["-y", "@tocharianou/mcp-server-kibana"],
"env": {
"KIBANA_URL": "http://localhost:5601",
"KIBANA_API_KEY": "your_encoded_api_key",
"KIBANA_DEFAULT_SPACE": "default",
"KIBANA_TIMEOUT": "30000"
}
}
}
}Prompts to try
These prompts demonstrate the server's dashboard management, log querying, and health check capabilities.
- "What is the current status of my Kibana server?"
- "Search for all dashboards that contain the word 'sales'."
- "Check the health of the dashboard named 'Infrastructure Overview'."
- "List all saved objects of type index-pattern."
- "Show me the dependencies for the 'Revenue Metrics' dashboard."Troubleshooting Kibana
Connection refused or ECONNREFUSED errors
Verify that KIBANA_URL is correct and that Kibana is running. For HTTPS endpoints with self-signed certificates, set KIBANA_CA_CERT to the path of your CA file or set NODE_TLS_REJECT_UNAUTHORIZED=0 (only for development).
401 Unauthorized when using API key
Kibana expects the API key in encoded form (base64 of 'id:api_key'). In the Kibana console, copy the 'encoded' value shown after creating the key, not the raw key ID.
Tools not appearing in the AI client
Ensure Node.js 18+ is installed and accessible in the PATH used by your MCP client. Run 'npx -y @tocharianou/mcp-server-kibana' in a terminal to confirm it starts without errors before adding it to the config.
Frequently Asked Questions about Kibana
What is Kibana?
Kibana is a Model Context Protocol (MCP) server that enables ai assistants to interact with kibana dashboards, visualizations, and elasticsearch data through read-only resources and executable tools for searching logs, exporting dashboards, and querying data. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Kibana?
Install via npm with the command: npx -y @tocharianou/mcp-server-kibana. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Kibana?
Kibana works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Kibana free to use?
Yes, Kibana is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.
Kibana Alternatives — Similar Monitoring & Observability Servers
Looking for alternatives to Kibana? Here are other popular monitoring & observability servers you can use with Claude, Cursor, and VS Code.
Netdata
★ 78.9kReal-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Kubeshark
★ 11.9keBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via MCP and humans via dashboard.
Mission Control
★ 4.9kSelf-hosted AI agent orchestration platform: dispatch tasks, run multi-agent workflows, monitor spend, and govern operations from one mission control dashboard.
Grafana
★ 3.0kThis MCP server enables natural-language querying of Grafana logs by automatically detecting log sources and service labels. It provides read-only access to log data with intelligent caching for efficient repeat queries.
Sentrux
★ 2.4kReal-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.
OpenInference
★ 986OpenTelemetry Instrumentation for AI Observability
Browse More Monitoring & Observability MCP Servers
Explore all monitoring & observability servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Kibana in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Kibana?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.