How to integrate Kibana MCP with Autogen

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Kibana logo
AutoGen logo
divider

Introduction

This guide walks you through connecting Kibana to AutoGen using the Composio tool router. By the end, you'll have a working Kibana agent that can visualize weekly sales data as a chart, list top error logs from last 24 hours, generate dashboard of user activity trends through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Kibana account through Composio's Kibana MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Kibana with

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Kibana
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Kibana tools
  • Run a live chat loop where you ask the agent to perform Kibana operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

What is the Kibana MCP server, and what's possible with it?

The Kibana MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Kibana account. It provides structured and secure access so your agent can perform Kibana operations on your behalf.

Supported Tools & Triggers

Tools
Delete Alerting RuleTool to delete an alerting rule in Kibana.
Delete ConnectorTool to delete a connector in Kibana.
Delete Fleet OutputTool to delete a specific output configuration in Kibana Fleet.
Delete Fleet ProxyDeletes a Fleet proxy configuration by its unique identifier.
Delete ListDeletes a list.
Delete Osquery Saved QueryDelete a saved Osquery query by its saved object ID.
Delete Saved ObjectTool to delete a saved object in Kibana.
Find Kibana AlertsTool to find and/or aggregate detection alerts in Kibana.
Get Action TypesRetrieves all available connector types (actions) in Kibana.
Get Alerting RulesTool to retrieve a list of alerting rules in Kibana.
Get Rule TypesRetrieves available rule types (alert types) in Kibana.
Get CasesTool to retrieve a list of cases in Kibana.
Get All ConnectorsTool to retrieve a list of all connectors in Kibana.
Get Data ViewsRetrieves all data views (formerly known as index patterns) available in Kibana.
Find Detection Engine RulesRetrieves a paginated list of Kibana detection engine rules with flexible filtering and sorting options.
Get Endpoint List ItemsRetrieves Elastic Endpoint exception list items with filtering, pagination, and sorting capabilities.
Get Entity Store EnginesRetrieves all entity store engines configured in Kibana.
List Entity Store EntitiesTool to list entity records in the entity store with support for paging, sorting, and filtering.
Get Entity Store StatusRetrieves the current status of the Kibana Entity Store and its configured engines.
Get Fleet Agent PoliciesRetrieves a paginated list of Fleet agent policies with filtering, sorting, and optional detailed information.
Get Fleet Agents Available VersionsTool to retrieve the available versions for Fleet agents.
Get Fleet Agents Setup StatusCheck Fleet setup readiness and identify missing requirements.
Check Fleet PermissionsTool to check the permissions for the Fleet API.
Get Fleet Enrollment API KeyTool to retrieve details of a specific enrollment API key by its ID.
Get Fleet Enrollment API KeysTool to fetch a list of enrollment API keys.
Get Fleet EPM CategoriesGet all available package categories in the Elastic Package Manager (EPM) with package counts.
Get Fleet EPM Data StreamsTool to retrieve the list of data streams in the Elastic Package Manager.
Get Fleet EPM Package DetailsRetrieves comprehensive details for a specific Fleet integration package version from the Elastic Package Manager (EPM).
Get Fleet EPM Package FileRetrieves a specific file from an Elastic Package Manager (EPM) package.
Get Fleet EPM PackagesTool to fetch the list of available packages in the Elastic Package Manager.
Get Installed EPM PackagesTool to retrieve the list of installed packages in the Elastic Package Manager.
Get Fleet EPM Packages (Limited)Retrieves a limited list of package names from the Elastic Package Manager (EPM) registry.
Get EPM Package StatisticsRetrieves usage statistics for a specific Fleet package in Kibana, including the number of package policies and agent policies using the package.
Get Fleet Package PoliciesRetrieves a list of Fleet package policies (integration policies) in Kibana.
Get Fleet Server HostTool to fetch details of a specific Fleet server host by its item ID.
Get Fleet Server HostsTool to retrieve the list of Fleet Server hosts.
Get Index Management IndicesTool to fetch information about indices managed by Kibana's Index Management feature.
Get Node MetricsTool to retrieve statistics for nodes in an Elasticsearch cluster, often visualized in Kibana.
Get Reporting JobsTool to retrieve a list of reporting jobs in Kibana.
Get Saved ObjectsTool to retrieve a list of saved objects in Kibana based on specified criteria.
Get Kibana StatusTool to get the current status of Kibana.
Create Alerting RuleTool to create a new alerting rule in Kibana.
Create CaseTool to create a new case in Kibana.
Create Kibana ConnectorTool to create a new connector in Kibana.
Create DashboardTool to create a new dashboard in Kibana.
Create Data ViewTool to create a new data view (index pattern) in Kibana.
Create or Update Saved ObjectTool to create or update a saved object in Kibana.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Kibana account you can connect to Composio
  • Some basic familiarity with Autogen and Python async

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Kibana via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Kibana connections to use

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Kibana session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["kibana"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Kibana tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Kibana assistant agent with MCP tools
    agent = AssistantAgent(
        name="kibana_assistant",
        description="An AI assistant that helps with Kibana operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Kibana tools from the workbench

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Kibana related question or task to the agent.\n")

# Conversation loop
while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Kibana tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Kibana and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Kibana session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["kibana"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Kibana assistant agent with MCP tools
        agent = AssistantAgent(
            name="kibana_assistant",
            description="An AI assistant that helps with Kibana operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Kibana related question or task to the agent.\n")

        # Conversation loop
        while True:
            user_input = input("You: ").strip()

            if user_input.lower() in ['exit', 'quit', 'bye']:
                print("\nGoodbye!")
                break

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into Kibana through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Kibana, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build Kibana MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Kibana MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Kibana MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Kibana MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Kibana MCP with Claude Cowork

Codex logo

Codex

Use Kibana MCP with Codex

OpenClaw logo

OpenClaw

Use Kibana MCP with OpenClaw

Hermes logo

Hermes

Use Kibana MCP with Hermes

CLI logo

CLI

Use Kibana MCP with CLI

Google ADK logo

Google ADK

Use Kibana MCP with Google ADK

LangChain logo

LangChain

Use Kibana MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Kibana MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Kibana MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Kibana MCP with LlamaIndex

CrewAI logo

CrewAI

Use Kibana MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Kibana MCP?

With a standalone Kibana MCP server, the agents and LLMs can only access a fixed set of Kibana tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Kibana and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with Autogen?

Yes, you can. Autogen fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Kibana tools.

Can I manage the permissions and scopes for Kibana while using Tool Router?

Yes, absolutely. You can configure which Kibana scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Kibana data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Get started for freeGet a demo↗