How to Use the Kibana MCP in Vercel AI SDK

Q: How do I manage Kibana space switches dynamically inside Vercel AI SDK?

Your agent calls listspaces to find available environments, then updates its context to target the correct space ID. You can pass the selected space parameter directly to subsequent tool calls like findsavedobjects within the same streaming session.

Q: What happens if a data view creation fails during streaming?

The createdataview tool returns a structured error payload that your MCP client streams directly to your error-boundary component. This lets your application display the exact mapping conflict to the user immediately.

Build live Kibana monitoring dashboards that stream real-time updates directly into your Next.js app using Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect Kibana to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Kibana saved objects with Vercel AI SDK

This MCP Server provides the `bulk_get_saved_objects` tool to pull visualization configurations and stream them directly to your React components. When your user asks for an update, the Vercel AI SDK streams the raw configuration straight to the browser without blocking the main thread. You don't have to wait for a massive payload to finish downloading before rendering. By combining `list_data_views` with streaming UI elements, your Next.js interface renders the structure first and populates index details as they arrive.

Create spaces and data views on the fly

The `create_space` tool lets your web application provision isolated workspaces in response to tenant actions. Your Vercel AI SDK agent executes this setup inline, creating the workspace and immediately configuring its initial structure. Once the space exists, the React frontend triggers `create_data_view` to wire up the correct Elasticsearch index patterns. This gives your users a fresh, ready-to-use analytics environment in under three seconds.

Instant rule adjustments from the UI

The `update_rule` tool allows your interface to modify alerting thresholds without requiring users to open the native elastic console. Your Vercel AI SDK application binds this tool to simple chat inputs, making alert tuning as fast as typing a single sentence. If an alert misbehaves, the agent calls `disable_rule` to silence the noise instantly. The live stream shows the rule status change in real-time, giving operators immediate visual confirmation of the system state.

Setup guide

Set up Kibana MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Kibana tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Kibana transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Use createMCPClient to connect to the server and pass the tools to streamText. When the agent calls `get_saved_object`, you can render the returned configuration directly inside your custom UI components.

Yes, because the MCP Server handles the connection lifecycle while your Edge Function executes the `import_saved_objects` call. The agent streams the progress of the import back to the browser, avoiding standard serverless timeout limits.

Your agent calls `list_spaces` to find available environments, then updates its context to target the correct space ID. You can pass the selected space parameter directly to subsequent tool calls like `find_saved_objects` within the same streaming session.

The `create_data_view` tool returns a structured error payload that your MCP client streams directly to your error-boundary component. This lets your application display the exact mapping conflict to the user immediately.

Your credentials and saved objects stay within Vinkius's isolated V8 sandbox and are never stored on external servers. Every request to fetch dashboard JSON or index patterns runs through this MCP connection, keeping your data secure.

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