Kibana MCP. Manage your entire observability stack via chat.

Q: How do I list all available Kibana spaces using the Kibana MCP?

You use listspaces to get a complete catalog of every workspace. This command gives you an overview of your entire observability setup, helping you know exactly where to look for specific dashboards.

Q: Can I update my user roles with the Kibana MCP?

Yes, you can modify permissions using createorupdaterole. This tool allows you to define or change what users and groups are allowed to view across your data views.

Q: What is the best way to move a dashboard between environments?

Use the copysavedobjects tool. It copies saved objects, ensuring that dashboards maintain their full configuration when moving from a test space to production.

Q: How do I find specific index patterns with the Kibana MCP?

You use findsavedobjects. Simply describe what you're looking for, and the agent searches across your entire instance catalog for matching saved objects.

Q: Does the Kibana MCP help me manage alerting rules?

Absolutely. You can find all existing alerts with findrules, or modify them using updaterule if a threshold needs adjusting, ensuring your system always monitors critical metrics.

Kibana connects your observability stack directly to any AI agent. Use this MCP to manage Kibana spaces, discover dashboards, search index patterns, and automate configuration changes across your Elastic Stack. It lets you control everything from creating roles to copying saved objects without leaving the chat window.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Give Claude and any AI agent real-world access

Manage Kibana Spaces

List, create, or delete entire workspaces (spaces) to organize dashboards for different teams.

Control Saved Objects

Create, read, update, and delete saved items like index patterns and visualizations across your instance.

Automate Role Permissions

Manage user roles by creating or updating specific Kibana permissions to control who sees what data.

Maintain Data Consistency

Copy saved objects between different spaces, ensuring your monitoring dashboards look the same in staging and production.

Audit System Components

Retrieve full metadata for any object—like a data view or an agent policy—so you can understand its current configuration.

Ask an AI about this

Waiting for input…

AI Agent

What AI agents can do with Kibana MCP: 55 Tools for Observability Management

These tools allow you to query, fetch, collect metrics, and administer every part of your Kibana instance using natural language commands.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using Kibana MCP

Add Case Comment

Adds a comment directly to an existing case record.

Bulk Create Saved Objects

Creates multiple saved objects at once using a bulk operation.

Bulk Get Saved Objects

Retrieves details for several saved objects simultaneously in one call.

Bulk Update Saved Objects

Updates multiple existing saved objects efficiently using a bulk operation.

Copy Saved Objects

Duplicates and copies saved objects from one Kibana space to another.

Create Agent Policy

Generates a new policy that controls the behavior of an Elastic Agent.

Create Case

Creates a brand-new case record within the system.

Create Connector

Sets up and creates a new data connector source.

Create Data View

Generates a specific view of the raw data for analysis purposes.

Create Enrollment Key

Creates a new key used to enroll agents into your system.

Create Or Update Role

Defines or modifies user roles and permissions within Kibana.

Create Rule

Creates a new alerting rule that triggers when metrics cross set thresholds.

Create Runtime Field

Adds or modifies a field in a data view without changing the original index structure.

Create Saved Object

Generates and saves a single object like an index pattern or dashboard.

Create Short Url

Creates a shortened, easily shareable URL for internal links.

Create Space

Establishes an entirely new, isolated Kibana workspace (space).

Delete Cases

Removes multiple case records from the system.

Delete Connector

Deletes an existing data connector source.

Delete Data View

Permanently removes a specific data view from use.

Delete Role

Removes a defined user role and all associated permissions.

Delete Rule

Deactivates or removes an alerting rule that monitors metrics.

Delete Saved Object

Permanently deletes a saved object, such as an index pattern or visualization.

Delete Short Url

Removes a previously created short URL.

Delete Space

Deletes an entire Kibana workspace, removing all contained dashboards and objects.

Disable Rule

Turns off a specific alerting rule without deleting its configuration.

Enable Rule

Restores an alerting rule, allowing it to start monitoring metrics again.

Execute Connector

Triggers a manual run of a configured data connector action.

Export Saved Objects

Generates export files containing sets of saved objects for archival or migration.

Find Rules

Searches the system to list all existing alerting rules and their status.

Find Saved Objects

Searches across your instance for specific saved objects using natural language queries.

Get Agent

Retrieves detailed information about a specific Elastic Agent installation.

Get Case

Fetches all details for an individual case record.

Get Connector

Retrieves detailed metadata about a specific data connector source.

Get Data View

Fetches the full configuration and definition of a particular data view.

Get Role

Retrieves all details about a specific Kibana user role, including permissions.

Get Rule

Fetches the current state and definition of an alerting rule.

Get Saved Object

Retrieves all metadata for a single, specified saved object type (like a dashboard or visualization).

Get Short Url

Gets the full details and destination URL of a short link.

Get Space

Retrieves all configuration details for a specific Kibana workspace.

Import Saved Objects

Imports multiple saved objects into the current space from an uploaded file.

List Agent Policies

Lists all available agent policies that can be applied to your endpoints.

List Agents

Provides a list of every Elastic Agent currently reporting into the system.

List Connectors

Retrieves a complete catalog and status report of all connected data sources.

List Data Views

Lists every available data view defined within your Kibana instance.

List Enrollment Keys

Provides a list of all active enrollment keys for agent setup.

List Roles

Lists every defined user role and their default permissions in Kibana.

List Spaces

Gets a list of all available, top-level Kibana workspaces across the instance.

Resolve Import Errors

Checks and reports on any errors that occurred during a bulk import process.

Search Cases

Searches the case management system using keywords or filters to find relevant records.

Unenroll Agent

Removes a specific Elastic Agent from monitoring and reporting within the stack.

Update Cases

Modifies details for existing case records, such as changing status or adding notes.

Update Data View

Makes modifications to an existing data view's definition and mapping settings.

Update Rule

Modifies the parameters, thresholds, or conditions of an active alerting rule.

Update Saved Object

Updates the configuration of any saved object, such as changing a dashboard's source data.

Update Space

Makes general modifications to an existing Kibana workspace's settings.

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The Kibana integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "kibana": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the Kibana tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

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

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on each call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with Kibana, then connect any of our 5,200+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,200+ others, all in one place
Add new capabilities to your AI anytime you want
Connections are secured and governed automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog weekly

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.

VINKIUS CLOUD

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on each call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

The Daily Pain of Observability Stack Management

Right now, managing your observability stack means clicking through a labyrinth of UI menus. You have to manually navigate between spaces, check roles in one tab, and then go back to another section just to list the saved objects you need. If you want to move a dashboard from staging to production, you're copying data in one place and updating permissions in three different tabs.

With this MCP, you treat your entire Kibana setup like a single system accessible through chat. You tell the agent what needs to happen—for example, 'Copy Dashboard X to Space Y.' The tool handles all the underlying steps: checking if the space exists, validating the object ID, and performing the copy operation—all without you touching a button.

Control Your Entire Stack with Kibana MCP

You eliminate redundant administrative tasks like checking if an index pattern is already defined or confirming which roles have viewing access. You don't have to remember the exact endpoint URL for every single object type; you just describe what you need done.

The difference now is control. Instead of being limited by a graphical user interface, your agent gives you programmatic power over every aspect of your data visualization layer.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

elastic-stack

dashboards

observability

data-visualization

kibana-api

What Kibana MCP does for your AI

Managing a large-scale monitoring platform like Kibana usually means jumping between dozens of tabs just to check settings or move visualizations. This MCP handles that complexity for you, letting your agent interact with your entire Elastic Stack through natural language commands. You can list and inspect spaces, find specific index patterns, or copy saved objects directly into different environments.

Need to change permissions? Use the tools here to create, update, or delete roles and even provision new agents. It's about controlling your data infrastructure from a single chat window. Vinkius makes it simple: connect once with any MCP-compatible client, and you get instant access to all these critical management functions.

Built · Hosted · Managed by Vinkius Kibana-MCP - Manage Observability Data & Views

Server ID 019e5d2a-ced9-72ea-a285-9f76c008effb

Vinkius Inspector

Compliance Grade A+

Score 98.33/100

Report View Report ↗

Benefits of connecting Kibana MCP

Instead of manually navigating to the 'list spaces' section, you simply ask your agent for a list of all available Kibana workspaces. This lets you immediately see every environment you manage, like finding all team-specific areas.

When you need consistency across environments, use copy_saved_objects. You can copy dashboards or index patterns between staging and production spaces with one command, guaranteeing that the view logic remains identical.

If a dashboard is broken because of outdated permissions, you don't have to find the right admin role. The tools let you create_or_update_role directly, fixing access control instantly through conversation.

Need to understand why something isn't showing up? You can use get_saved_object or find_saved_objects to pull all metadata on an index pattern, telling you its exact configuration and last updated time without clicking anything.

Setting up a new alert used to be tedious. Now, the agent handles it; just tell it what metrics to watch, and use create_rule or update_rule to build and fine-tune alerts automatically.

Kibana MCP use cases

01 01

Migrating a Dashboard from Test to Prod

A SRE needs to move the 'API Latency Overview' dashboard from their testing space to the main production monitoring space. They ask the agent, and it runs copy_saved_objects, instantly making sure the dashboard is available in the correct location without manual clicking or file transfer.

02 02

Auditing User Permissions for Compliance

A Platform Engineer must verify that only senior team members can see certain logs. They use list_roles to see all roles, and then ask the agent to run get_role on 'Security-Admins' to confirm they have access to the necessary data views.

03 03

Fixing a Missing Index Pattern

A Data Analyst realizes that the new log source isn't appearing. They ask the agent to find_saved_objects using keywords like 'new service logs', and it points them to the exact index pattern they need, saving hours of searching.

04 04

Scaling Up Observability Infrastructure

A DevOps lead needs to set up a dedicated workspace for a new product team. They instruct the agent to create_space and then immediately run list_connectors to ensure all necessary data sources are available in that fresh environment.

Kibana MCP tradeoffs

What to watch out for, and the recommended way to handle each one.

Trying to fix permissions manually

Avoid

A user gets the error 'Permission Denied' when viewing a dashboard and spends 30 minutes clicking through settings menus trying to figure out which role needs updating.

Instead

Instead, ask your agent to get_role details. If you find the right role, use create_or_update_role or update_saved_object to apply the necessary changes directly.

Manually searching for old data views

Avoid

A team member needs a specific visualization but can't remember its name, forcing them to manually check every single data view in the list.

Instead

Use find_saved_objects and give your agent a natural language description of what you need. It searches the whole instance for you.

Rebuilding dashboards from scratch

Avoid

A team member loses access to an old, complex dashboard and spends days trying to recreate all visualizations using raw data streams.

Instead

If they can't find the object, ask the agent to get_saved_object by ID or name. If it exists but is broken, use update_saved_object with the latest configuration details.

When to use Kibana MCP

Use this MCP if your workflow involves managing multiple, interdependent components within Kibana: spaces, roles, saved objects, and alerting rules. This tool excels when you need to perform auditing actions (like list_roles or get_space) or mass configuration changes (bulk_create_saved_objects). Don't use it if your goal is purely exploratory data analysis—if you just want to run a query on live logs, that's better handled by the Kibana UI itself. However, if the problem is managing the infrastructure that powers the visualization (e.g., setting up access control or copying dashboards), this MCP is essential because it exposes all those administrative tools via conversation.

Frequently asked questions about Kibana MCP

How do I list all available Kibana spaces using the Kibana MCP? +

You use list_spaces to get a complete catalog of every workspace. This command gives you an overview of your entire observability setup, helping you know exactly where to look for specific dashboards.

Can I update my user roles with the Kibana MCP? +

Yes, you can modify permissions using create_or_update_role. This tool allows you to define or change what users and groups are allowed to view across your data views.

What is the best way to move a dashboard between environments? +

Use the copy_saved_objects tool. It copies saved objects, ensuring that dashboards maintain their full configuration when moving from a test space to production.

How do I find specific index patterns with the Kibana MCP? +

You use find_saved_objects. Simply describe what you're looking for, and the agent searches across your entire instance catalog for matching saved objects.

Does the Kibana MCP help me manage alerting rules? +

Absolutely. You can find all existing alerts with find_rules, or modify them using update_rule if a threshold needs adjusting, ensuring your system always monitors critical metrics.