How to Use the Kibana MCP in CrewAI

Q: Can a CrewAI agent update a Kibana data view mapping autonomously?

Yes, your data engineer agent can call getdataview to analyze the current fields, determine missing mappings, and execute updatedataview to apply the correction without human intervention.

Deploy a team of specialized CrewAI agents to audit Kibana spaces, manage alerting rules, and resolve active cases.

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 CrewAI

Create your Vinkius account to connect Kibana to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run CrewAI agents to audit Kibana spaces

This MCP Server provides the `list_spaces` tool so your audit agent can map out the entire cluster layout. The auditor agent hands this list to a cleanup agent, which uses `delete_space` to remove abandoned environments based on your retention policies. Before any deletion, a third moderator agent runs `export_saved_objects` to back up the dashboards. This multi-agent coordination ensures you never lose critical configurations during routine maintenance.

Automated incident response and triage

The `get_case` tool allows your triage agent to pull active incident details the moment a rule triggers. The triage agent analyzes the case description and assigns a specialized response agent to gather diagnostic data. The response agent then executes `add_case_comment` to post the relevant search queries and logs directly into the ticket. This complete cycle happens autonomously, saving your on-call engineers ten minutes of manual investigation per alert.

Dynamic agent policy management

The `create_agent_policy` tool lets your infrastructure agent roll out fresh configuration baselines across your fleet. Working in tandem, a monitoring agent runs `list_agents` to identify which hosts require the new policy assignment. If an agent behaves abnormally, the crew triggers `unenroll_agent` to isolate the host immediately. This immediate, coordinated reaction keeps your telemetry pipeline clean and secure without requiring manual intervention.

Setup guide

Set up Kibana MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Kibana tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Kibana Analyst",
    goal="Access and analyze Kibana data via MCP.",
    backstory="Expert analyst with direct Kibana access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Kibana transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Kibana Analyst",
        goal="Access and analyze Kibana data via MCP.",
        backstory="Expert analyst with direct Kibana access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Kibana transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Agents use CrewAI's shared memory to pass the active space ID and dashboard configurations retrieved via `get_saved_object`. This ensures the triage agent and the response agent are always looking at the exact same telemetry.

Yes, your data engineer agent can call `get_data_view` to analyze the current fields, determine missing mappings, and execute `update_data_view` to apply the correction without human intervention.

You use the tool filter option in your MCP configuration to only expose `find_rules` and `get_rule`. This prevents the agent from executing destructive actions like `delete_rule` or changing production thresholds.

CrewAI's task sequencing prevents simultaneous writes by executing the updates in order across the MCP connection. The agent uses `update_saved_object` and checks the returned version number to prevent overwriting parallel changes.

All communication between your CrewAI agents and the Kibana instance is encrypted end-to-end via the MCP Server gateway. Your case comments, alert rules, and user roles are processed in memory and never written to persistent disk storage within the sandbox.

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