How to integrate Better stack MCP with LlamaIndex

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

30 min · no commitment · see it on your stack

Better stack logo
LlamaIndex logo
divider

Introduction

This guide walks you through connecting Better stack to LlamaIndex using the Composio tool router. By the end, you'll have a working Better stack agent that can show uptime percentage for api monitor, create escalation policy for on-call team, list heartbeat availability for last week through natural language commands.

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

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

Also integrate Better stack with

TL;DR

Here's what you'll learn:
  • Set your OpenAI and Composio API keys
  • Install LlamaIndex and Composio packages
  • Create a Composio Tool Router session for Better stack
  • Connect LlamaIndex to the Better stack MCP server
  • Build a Better stack-powered agent using LlamaIndex
  • Interact with Better stack through natural language

What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.

Key features include:

  • ReAct Agent: Reasoning and acting pattern for tool-using agents
  • MCP Tools: Native support for Model Context Protocol
  • Context Management: Maintain conversation context across interactions
  • Async Support: Built for async/await patterns

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

The Better stack MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Better Stack account. It provides structured and secure access to your monitoring, logging, and incident management tools, so your agent can perform actions like retrieving uptime metrics, managing escalation policies, checking heartbeat statuses, and organizing log sources on your behalf.

  • Monitor health checks and availability: Let your agent fetch uptime percentages, availability summaries, and incident details for any monitor in your stack.
  • Automated escalation policy management: Instruct your agent to create or delete escalation policies, keeping your incident response workflows up-to-date without manual effort.
  • Heartbeat tracking and organization: Have your agent fetch specific heartbeat data, check heartbeat availability, or group related heartbeats for easier monitoring.
  • Log source grouping and management: Enable your agent to create or delete source groups, helping you organize log streams and maintain a tidy observability structure.
  • Webhook integration setup: Direct your agent to register outgoing webhooks so your stack can notify external systems of important events automatically.

Supported Tools & Triggers

Tools
Acknowledge IncidentTool to acknowledge an ongoing incident.
Create Escalation PolicyCreates a new escalation policy for incident management.
Create HeartbeatTool to create a new heartbeat monitor for cron jobs and scheduled tasks.
Create Heartbeat GroupTool to create a new heartbeat group.
Create IncidentTool to create a new incident and alert the on-call person.
Create Incident CommentTool to create a new comment on an incident.
Create MetadataTool to create or update a metadata record for a resource.
Create MonitorTool to create a new uptime monitor for a URL or service.
Create Monitor GroupTool to create a new monitor group.
Create On-Call ScheduleTool to create a new on-call schedule.
Create Outgoing Webhook IntegrationTool to create a new outgoing webhook integration.
Create Escalation Policy GroupTool to create a new escalation policy group.
Create Source GroupTool to create a new source group.
Create Status Page GroupTool to create a new status page group.
Create Status Page ReportTool to create a new status page report (incident or maintenance).
Create Status Page ResourceTool to create a new status page resource.
Create Status Page SectionTool to create a new section on a status page.
Create Status UpdateTool to create a new status update for an existing status report.
Create Severity LevelTool to create a new severity level (urgency) for incident management.
Create Urgency GroupTool to create a new urgency group (severity group) for incident categorization.
Delete Escalation PolicyTool to delete an escalation policy by ID.
Delete HeartbeatTool to permanently delete a heartbeat by ID.
Delete Heartbeat GroupTool to permanently delete a heartbeat group by ID.
Delete IncidentTool to permanently delete an existing incident by ID.
Delete Incident CommentTool to delete an existing comment from an incident.
Delete MonitorTool to permanently delete a monitor by ID from Better Stack Uptime.
Delete Monitor GroupTool to permanently delete a monitor group by ID from Better Stack Uptime.
Delete On-Call ScheduleTool to permanently delete an on-call schedule by ID.
Delete Outgoing Webhook IntegrationTool to delete an outgoing webhook integration by ID.
Delete Escalation Policy GroupTool to delete an escalation policy group by ID.
Delete Source GroupTool to permanently delete a source group by ID from Better Stack Telemetry (Logs).
Delete Status Page GroupTool to delete a status page group by ID.
Delete Status Page ReportTool to permanently delete a status page report by ID from Better Stack Uptime.
Delete Status Page ResourceTool to delete an existing resource from a status page.
Delete Status Page SectionTool to permanently delete a status page section by ID.
Delete Status UpdateTool to delete an existing status update from a status report.
Delete SeverityTool to delete a severity (urgency) by ID.
Delete Urgency GroupTool to permanently delete an urgency group (severity group) by ID.
Escalate IncidentTool to escalate an ongoing incident to a user, team, schedule, policy, or organization.
Get Escalation PolicyTool to get a single escalation policy by its ID.
Get HeartbeatTool to get a single heartbeat by ID.
Get Heartbeat AvailabilityTool to retrieve availability summary for a specific heartbeat.
Get Heartbeat GroupTool to get a single heartbeat group by ID.
Get Incident CommentTool to get a single comment from an incident.
Get MonitorTool to get a single monitor.
Get Monitor AvailabilityTool to return an availability summary for a specific monitor.
Get Monitor GroupTool to get a single monitor group by ID.
Get Monitor Group's MonitorsTool to get all monitors belonging to a monitor group.
Get Monitor Response TimesRetrieves response time performance metrics for a specific uptime monitor.
Get On-Call ScheduleTool to get a single on-call schedule by ID.
Get Outgoing Webhook IntegrationTool to get a single outgoing webhook integration by ID.
Get Escalation Policy GroupTool to get a single escalation policy group.
Get Status PageTool to get a single status page by ID.
Get Status Page GroupTool to get a single status page group by ID.
Get Status Page ReportTool to get a single status page report by ID.
Get Status Page ResourceTool to get a single status page resource by ID.
Get Status Page SectionTool to get a single status page section.
Get Status UpdateTool to get a single status update by its ID.
Get Uptime API TokenTool to retrieve the configured Uptime API token.
Get Severity LevelTool to get a single severity level (urgency) by ID.
Get Urgency GroupTool to get a single urgency group (severity group) by ID.
List AWS CloudWatch IntegrationsTool to list all AWS CloudWatch integrations.
List Azure IntegrationsTool to list all Azure integrations.
List Catalog RelationsTool to list all catalog relations.
List Datadog IntegrationsTool to list all Datadog integrations.
List Elastic IntegrationsTool to list Elastic integrations.
List Email IntegrationsTool to list email integrations.
List Google Monitoring IntegrationsTool to list all Google Monitoring integrations.
List Grafana IntegrationsTool to list all Grafana integrations.
List Heartbeat GroupsTool to list all heartbeat groups.
List HeartbeatsTool to list all heartbeats.
List Incidents CommentsTool to list all comments on an incident.
List Incidents TimelineTool to retrieve all timeline events for an incident.
List Incidents UptimeTool to list all incidents with optional filtering by monitor, heartbeat, date range, or resolution status.
List Jira IntegrationsTool to list all Jira integrations.
List MetadataTool to list all existing metadata.
List Monitor GroupsTool to list all monitor groups.
List MonitorsTool to list all monitors.
List New Relic IntegrationsTool to list New Relic integrations.
List On-Call Schedule EventsTool to list all events for a specific on-call schedule.
List On-Call SchedulesTool to list all on-call schedules.
List Outgoing Webhook IntegrationsTool to list all outgoing webhook integrations.
List PagerDuty WebhooksTool to list PagerDuty integrations.
List Escalation PoliciesTool to list all escalation policies.
List Escalation Policy GroupsTool to list all escalation policy groups.
List Prometheus IntegrationsTool to list all Prometheus integrations.
List Single IncidentTool to retrieve detailed information about a single incident by its ID.
List Slack IntegrationsTool to list all Slack integrations.
List Splunk On-Call IntegrationsTool to list all Splunk On-Call integrations.
List Status Page GroupsTool to list all status page groups.
List Status Pages In Status Page GroupTool to list status pages within a specific status page group.
List Status Page ReportsTool to list all reports on a status page.
List Status Page Report Status UpdatesTool to list all status updates for a status page report.
List Status PagesTool to list all your status pages.
List Status Page SectionsTool to list all sections of a specific status page.
List Status Page ResourcesTool to list all resources on a status page.
List Severity LevelsTool to list all severity levels (urgencies).
List Urgency GroupsTool to list all urgency groups (severity groups).
Resolve IncidentTool to resolve an ongoing incident.
Update Escalation PolicyTool to update an existing escalation policy.
Update HeartbeatTool to update an existing heartbeat configuration.
Update Heartbeat GroupUpdates an existing heartbeat group's properties.
Update Incident CommentTool to update an existing comment on an incident.
Update MonitorTool to update an existing uptime monitor configuration.
Update Monitor GroupUpdates an existing monitor group's properties.
Update On-Call ScheduleTool to update an on-call schedule's name.
Update Outgoing Webhook IntegrationTool to update an existing outgoing webhook integration.
Update Escalation Policy GroupUpdates an existing escalation policy group's properties.
Update Source GroupUpdate an existing source group in Better Stack Logs/Telemetry.
Update Status Page GroupTool to update an existing status page group.
Update Status Page ReportTool to update an existing status page report.
Update Status Page ResourceTool to update an existing status page resource.
Update Status PagesTool to update an existing status page configuration.
Update Status Page SectionTool to update an existing status page section.
Update Status UpdateTool to update an existing status update for a status report.
Update Severity LevelTool to update an existing severity level (urgency) configuration.
Update Urgency GroupTool to update an existing urgency group (severity group).

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

Before you begin, make sure you have:
  • Python 3.8/Node 16 or higher installed
  • A Composio account with the API key
  • An OpenAI API key
  • A Better stack account and project
  • Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Better stack

OpenAI API key (OPENAI_API_KEY)
  • Go to the OpenAI dashboard
  • Create an API key if you don't have one
  • Assign it to OPENAI_API_KEY in .env
Composio API key and user ID
  • Log into the Composio dashboard
  • Copy your API key from Settings
    • Use this as COMPOSIO_API_KEY
  • Pick a stable user identifier (email or ID)
    • Use this as COMPOSIO_USER_ID

Installing dependencies

pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv

Create a new Python project and install the necessary dependencies:

  • composio-llamaindex: Composio's LlamaIndex integration
  • llama-index: Core LlamaIndex framework
  • llama-index-llms-openai: OpenAI LLM integration
  • llama-index-tools-mcp: MCP client for LlamaIndex
  • python-dotenv: Environment variable management

Set environment variables

bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id

Create a .env file in your project root:

These credentials will be used to:

  • Authenticate with OpenAI's GPT-5 model
  • Connect to Composio's Tool Router
  • Identify your Composio user session for Better stack access

Import modules

import asyncio
import os
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

Create a new file called better stack_llamaindex_agent.py and import the required modules:

Key imports:

  • asyncio: For async/await support
  • Composio: Main client for Composio services
  • LlamaIndexProvider: Adapts Composio tools for LlamaIndex
  • ReActAgent: LlamaIndex's reasoning and action agent
  • BasicMCPClient: Connects to MCP endpoints
  • McpToolSpec: Converts MCP tools to LlamaIndex format

Load environment variables and initialize Composio

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set in the environment")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment")

What's happening:

This ensures missing credentials cause early, clear errors before the agent attempts to initialise.

Create a Tool Router session and build the agent function

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["better_stack"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")

    description = "An agent that uses Composio Tool Router MCP tools to perform Better stack actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Better stack actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)

What's happening here:

  • We create a Composio client using your API key and configure it with the LlamaIndex provider
  • We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, better stack)
  • The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
  • LlamaIndex will connect to this endpoint to dynamically discover and use the available Better stack tools.
  • The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.

Create an interactive chat loop

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

What's happening here:

  • We're creating a direct terminal interface to chat with your Better stack database
  • The LLM's responses are streamed to the CLI for faster interaction.
  • The agent uses context to maintain conversation history
  • You can type 'quit' or 'exit' to stop the chat loop gracefully
  • Agent responses and any errors are displayed in a clear, readable format

Define the main entry point

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

What's happening here:

  • We're orchestrating the entire application flow
  • The agent gets built with proper error handling
  • Then we kick off the interactive chat loop so you can start talking to Better stack

Run the agent

npx ts-node llamaindex-agent.ts

When prompted, authenticate and authorise your agent with Better stack, then start asking questions.

Complete Code

Here's the complete code to get you started with Better stack and LlamaIndex:

import asyncio
import os
import signal
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["better_stack"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")
    description = "An agent that uses Composio Tool Router MCP tools to perform Better stack actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Better stack actions.
    """
    return ReActAgent(
        tools=tools,
        llm=llm,
        description=description,
        system_prompt=system_prompt,
        verbose=True,
    );

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

Conclusion

You've successfully connected Better stack to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:
  • Tool Router dynamically exposes Better stack tools through an MCP endpoint
  • LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
  • The agent becomes more capable without increasing prompt size
  • Async Python provides clean, efficient execution of agent workflows
You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.

How to build Better stack MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Better stack MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Better stack MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Better stack MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Better stack MCP with Claude Cowork

Codex logo

Codex

Use Better stack MCP with Codex

OpenClaw logo

OpenClaw

Use Better stack MCP with OpenClaw

Hermes logo

Hermes

Use Better stack MCP with Hermes

CLI logo

CLI

Use Better stack MCP with CLI

Google ADK logo

Google ADK

Use Better stack MCP with Google ADK

LangChain logo

LangChain

Use Better stack MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Better stack MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Better stack MCP with Mastra AI

CrewAI logo

CrewAI

Use Better stack MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Better stack MCP?

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

Can I use Tool Router MCP with LlamaIndex?

Yes, you can. LlamaIndex 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 Better stack tools.

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

Yes, absolutely. You can configure which Better stack 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 Better stack 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↗