How to Use the Kibana MCP in Mastra AI

Q: How does Mastra AI handle failures when creating a Kibana data view?

The workflow engine intercepts errors from createdataview and triggers a configured retry policy. If the index pattern is missing, the agent can branch to check active indices before attempting the creation again.

Q: Can I require manual approval before Mastra AI deletes a Kibana space?

Yes, you can configure the requireToolApproval flag on the deletespace tool within your MCP client setup. The workflow pauses and waits for a manual override before executing the deletion.

Q: How do I sync Kibana alerting rules across regions using Mastra AI?

Your workflow calls findrules in the source region, parses the output, and iterates through the list to run createrule in the target region. The built-in workflow engine manages this sequence, tracking successes and failures for each rule.

Q: How do I handle conflicts during bulk object updates?

The bulkupdatesavedobjects tool returns a list of failed updates, which your MCP client passes to a conditional branch. The agent then resolves conflicts individually using updatesavedobject for the affected IDs.

Automate Kibana space migrations and alert management with Mastra AI workflows that handle API failures gracefully.

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 Mastra AI

Create your Vinkius account to connect Kibana to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Kibana migrations with Mastra AI workflows

This MCP Server exposes the `copy_saved_objects` tool to move dashboards and visualizations between separate environments. When running inside a Mastra AI workflow, you can chain this tool with validation steps to guarantee that your production configurations migrate cleanly. If the target space is missing, the workflow branches to execute `create_space` first. The engine handles the dependency logic, ensuring your dashboards never land in a non-existent destination.

Auto-retrying alert rule deployments

The `create_rule` tool lets your automated agents deploy alerting configurations across multiple clusters. Mastra AI wraps this tool in a resilient workflow loop, meaning any transient network hiccups trigger automatic retries with exponential backoff. If a rule configuration fails validation, the workflow routes the error to `resolve_import_errors`. This lets your agent fix minor syntax issues in the rule parameters without crashing the entire deployment pipeline.

Human-approved incident escalation

The `create_case` tool initiates incident tracking directly within your security operations center space. Mastra AI coordinates this by generating the ticket and then pausing execution until a human operator approves the escalation. Once approved, the agent runs `add_case_comment` to append the latest diagnostic logs automatically. This keeps your human analysts and automated workflows perfectly synced during high-pressure outages.

Setup guide

Set up Kibana MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Kibana tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "kibana-mcp-client",
  servers: {
    "kibana-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Kibana Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Kibana tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Kibana transactions"
);
console.log(result.text);

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 Mastra AI

The workflow engine intercepts errors from `create_data_view` and triggers a configured retry policy. If the index pattern is missing, the agent can branch to check active indices before attempting the creation again.

Yes, you can configure the requireToolApproval flag on the `delete_space` tool within your MCP client setup. The workflow pauses and waits for a manual override before executing the deletion.

Your workflow calls `find_rules` in the source region, parses the output, and iterates through the list to run `create_rule` in the target region. The built-in workflow engine manages this sequence, tracking successes and failures for each rule.

The `bulk_update_saved_objects` tool returns a list of failed updates, which your MCP client passes to a conditional branch. The agent then resolves conflicts individually using `update_saved_object` for the affected IDs.

Yes, because your connection token is managed directly by the secure Vinkius gateway. No raw credentials, space configurations, or agent policies are cached, and every execution of `list_spaces` runs inside an isolated, temporary MCP runtime environment.

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