How to Use the Kibana MCP in OpenAI Agents SDK

Q: How do I connect the Kibana MCP Server to the OpenAI Agents SDK?

Install the openai-agents package via pip. Create an MCPServerStreamableHttp instance with your Vinkius endpoint and pass it to the mcpservers list in your Agent constructor.

Let your agent manage Kibana spaces directly through the OpenAI Agents SDK using this MCP Server.

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 OpenAI Agents SDK

Create your Vinkius account to connect Kibana to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Kibana MCP Server for production agents

You don't want an agent blindly deleting observability dashboards. When you connect this server, OpenAI's built-in guardrails validate every single request before execution. Your agent uses tools like `find_saved_objects` and `get_data_view` to read the environment state, while you define strict handoff boundaries for destructive actions. The integration relies on auto-discovery. Pass the endpoint to the agent constructor, and it instantly maps all 55 Kibana operations. You get full visibility into `create_space` or `update_rule` calls directly within your OpenAI dashboard tracing logs.

Automate incident response rules

Managing alerting rules manually across dozens of spaces wastes time. Your agent dynamically adjusts thresholds based on active incidents. It pulls existing configurations via `find_rules` and immediately fires `update_rule` to tune the noise down during a known outage. If an alert triggers a major event, the agent keeps working. It interacts with the incident management workflow using `create_case` and appends investigation details with `add_case_comment`. You build a closed-loop response system without writing custom API glue code.

Mass dashboard migrations

Moving configurations between environments usually involves fragile bash scripts. This setup lets your agent handle the heavy lifting. It executes `export_saved_objects` from the staging space and pushes the ndjson payload to production using `import_saved_objects`. Conflicts happen during deployments. When an import fails due to existing index patterns, the agent catches the exact failure state. It then runs `resolve_import_errors` to map the missing dependencies automatically.

Setup guide

Set up Kibana MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Kibana tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Kibana tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Kibana tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Kibana Agent",
            instructions="You have access to Kibana tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the `openai-agents` package via pip. Create an `MCPServerStreamableHttp` instance with your Vinkius endpoint and pass it to the `mcp_servers` list in your Agent constructor.

Yes. Auto-discovery handles the mapping. Once connected, your agent instantly recognizes operations like `list_spaces` and `get_connector` without any manual configuration.

You handle this through agent guardrails and native role-based access control. Limit the API token provided to the connection so it only has permissions for specific spaces, preventing accidental modifications via `update_space`.

The API returns the exact failure state directly to the agent. Because OpenAI traces every step, you review the exact `bulk_create_saved_objects` payload in your dashboard and see why specific dashboards were rejected.

Your agent reads sensitive alerting thresholds and incident cases directly from your observability stack. Vinkius isolates this connection inside a V8 sandbox with ephemeral memory. Zero data persists on our infrastructure after the session closes.

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