How to Use the Kibana MCP in Windsurf

Q: Can Windsurf Cascade migrate Kibana saved objects?

Yes. Cascade strings together exportsavedobjects and importsavedobjects to move dashboards between spaces. It handles the dependency resolution automatically.

Q: What happens if an import fails?

The server exposes the resolveimporterrors tool. Cascade reads the error response, fixes the missing index patterns, and retries the upload.

Q: How does Windsurf manage Kibana alerting rules?

You write the logic in your IDE. Cascade uses createrule to push it to the cluster, or findrules to audit what is currently running.

Let Windsurf's Cascade agent build and migrate your Kibana dashboards without asking for permission at every step.

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 Windsurf

Create your Vinkius account to connect Kibana to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Windsurf MCP Server for Observability

The Kibana MCP server connects your Windsurf environment directly to your Elastic stack. Cascade uses `list_spaces` and `find_saved_objects` to map out your current observability setup before touching a single configuration file. Tell the agent to clone a production dashboard for a staging environment. It will execute `export_saved_objects`, swap the underlying index references in the ndjson file, and run `import_saved_objects` into the target space. You just watch the logs roll in.

Chain Alerting Rule Deployments

Managing detection logic manually takes too long. Cascade pulls your local YAML rule definitions and pushes them live using `create_rule` or `update_rule`. If a rule triggers too much noise, you don't need to open the browser. Just ask your agent to shut it down. It fires `disable_rule` and immediately updates the corresponding incident ticket using `update_cases`.

Autonomous Fleet Provisioning

Windsurf handles Elastic Agent rollouts right from your editor. It runs `list_agent_policies` to find the correct baseline, then generates access credentials via `create_enrollment_key`. When you need to deprecate old infrastructure, the agent finds stale endpoints with `list_agents` and strips them out using `unenroll_agent`. No clicking through the Fleet UI required.

Setup guide

Set up Kibana MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Kibana payment history." If connected, Cascade will call the Kibana tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "kibana-mcp": {
      "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 Windsurf

Open Settings, go to Cascade, and find the MCP Servers UI. You can either use the built-in marketplace for a one-click install or edit your `~/.codeium/windsurf/mcp_config.json` file to add the Vinkius endpoint token.

Yes. Cascade strings together `export_saved_objects` and `import_saved_objects` to move dashboards between spaces. It handles the dependency resolution automatically.

The server exposes the `resolve_import_errors` tool. Cascade reads the error response, fixes the missing index patterns, and retries the upload.

You write the logic in your IDE. Cascade uses `create_rule` to push it to the cluster, or `find_rules` to audit what is currently running.

Vinkius runs the connection inside a zero-trust V8 isolate. The agent only reads the specific saved objects, agent policies, and case logs you target. Your actual ingested log data stays in Elasticsearch, while the ephemeral sandbox drops all state after execution.

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