How to Use the Kibana MCP in Claude Code

Q: How do I add the Kibana MCP server to Claude Code?

Run claude mcp add --transport http kibana -- . Make sure to put the transport flag before the server name. The config saves to /.claude.json.

Q: How do I verify the server is connected?

Type claude mcp list in your terminal. You should see the Kibana integration active and exposing tools like getspace and listdataviews.

Q: Can Claude Code export Kibana dashboards to my local repo?

It handles this perfectly. The agent executes exportsavedobjects and writes the resulting ndjson output directly to your local file system.

Manage your Elastic stack directly from the terminal with Claude Code and automate your observability pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kibana MCP to Claude Code

Create your Vinkius account to connect Kibana to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Kibana with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless Kibana MCP Server Access

The Kibana MCP server turns Claude Code into a command-line administrator for your Elastic environment. You can pipe a list of new engineers into the terminal, and the agent will run `create_or_update_role` to provision their access. Offboarding is just as fast. A cron job triggers the CLI, which executes `delete_role` and `delete_space` to scrub former employee environments. No web interface needed.

Script Incident Workflows

Sharing dashboards during an outage usually means copying massive URLs. Claude Code fixes this by calling `create_short_url` and dropping the clean link directly into your Slack pipeline. When an alert fires, your CI script can ask the agent to investigate. It runs `search_cases` to find similar past incidents, reads the history with `get_case`, and outputs a summary right to standard out.

Cross-Space Synchronization

Keeping multiple environments aligned is a massive headache. You can tell Claude Code to sync staging and production, prompting it to fire `copy_saved_objects` across the designated spaces. It cleans up after itself too. The agent identifies orphaned visualizations using `find_saved_objects` and purges them with `delete_saved_object` to keep your Kibana instance lean.

Setup guide

Set up Kibana MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see kibana-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Kibana transactions." It will automatically discover and invoke the available Kibana tools.

Terminal

claude mcp add --transport http kibana-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Kibana MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "kibana-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Kibana. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Kibana now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Kibana MCP in Claude Code

Run `claude mcp add --transport http kibana -- `. Make sure to put the transport flag before the server name. The config saves to `~/.claude.json`.

Yes. You can trigger shell scripts that instruct the agent to run `enable_rule` or `disable_rule` based on deployment events.

Type `claude mcp list` in your terminal. You should see the Kibana integration active and exposing tools like `get_space` and `list_data_views`.

It handles this perfectly. The agent executes `export_saved_objects` and writes the resulting ndjson output directly to your local file system.

Your enrollment keys, agent policies, and user roles pass through a secured, isolated sandbox. Vinkius drops the environment the moment your terminal session closes, ensuring zero persistent storage of your infrastructure secrets.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript