How to integrate Pushover MCP with LlamaIndex

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

30 min · no commitment · see it on your stack

Pushover logo
LlamaIndex logo
divider

Introduction

This guide walks you through connecting Pushover to LlamaIndex using the Composio tool router. By the end, you'll have a working Pushover agent that can send device alert for server downtime, notify me of new support tickets, push daily summary to your phone through natural language commands.

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

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

Also integrate Pushover 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 Pushover
  • Connect LlamaIndex to the Pushover MCP server
  • Build a Pushover-powered agent using LlamaIndex
  • Interact with Pushover 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 Pushover MCP server, and what's possible with it?

The Pushover MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Pushover account. It provides structured and secure access to your notification system, so your agent can send instant alerts, deliver custom messages, manage notification priorities, and automate device notifications on your behalf.

  • Instant push notifications: Have your agent send real-time alerts to your devices for important events, tasks, or reminders.
  • Custom message delivery: Allow your agent to craft and deliver personalized notifications with specific titles, messages, and sounds.
  • Priority and sound control: Let the agent set notification priority levels and choose custom sounds to ensure the right alerts stand out.
  • Device targeting: Direct your agent to send notifications to specific devices or user groups for tailored communication.
  • Automated workflow integration: Seamlessly trigger Pushover alerts from other automated tasks or events managed by your agent, keeping you informed in real-time.

Supported Tools & Triggers

Tools
Cancel Receipt RetriesTool to cancel further retries for an emergency-priority message before its expiry.
Cancel Retries by TagTool to cancel retries for all active emergency-priority Pushover messages matching a specific tag.
Client Acknowledge Delete Up To IDTool to delete/acknowledge device messages up to a specific message ID.
Fetch Pending MessagesTool to download pending messages for a registered device.
Pushover Client LoginTool to authenticate a Pushover user by email and password.
Client Realtime WebSocket ConnectionTool to establish a secure WebSocket connection for real-time message notifications.
Register Open Client DeviceTool to register an Open Client desktop device.
Get Application Icon ImageTool to fetch an application icon PNG by icon identifier.
Get App LimitsTool to retrieve the current monthly message limit, remaining messages, and reset time for a Pushover application.
Get Application TokenTool to fetch stored Pushover application API token.
Get Receipt StatusTool to poll the status of an emergency-priority notification receipt.
Get Team API TokenTool to fetch stored Pushover for Teams API token.
Glances UpdateTool to update a user's Glances widget data without sending a notification.
Add User to GroupTool to add an existing Pushover user to a delivery group.
Create GroupTool to create a new Delivery Group.
Disable Group UserTool to temporarily disable deliveries to a user or specific device within a Pushover group.
Group Enable UserTool to re-enable deliveries to a previously disabled user (or specific device) within a Pushover group.
Get Group DetailsTool to retrieve details for a Delivery Group.
List Delivery GroupsTool to list all Delivery Groups.
Remove User from GroupTool to remove a user (or optionally a specific device) from a Pushover delivery group.
Rename Delivery GroupTool to rename an existing Delivery Group.
Assign LicenseTool to assign a pre-paid license credit to a Pushover user by key or email.
Check License CreditsTool to retrieve remaining license credits for a Pushover application.
Send MessageTool to send a push notification with optional title, URL, priority, sound, attachments, and filters.
Store Team API TokenTool to securely store a Pushover for Teams API token.
Subscription FlowTool to validate and return a Pushover subscription code.
Add Team UserTool to add a user to a Pushover for Teams organization.
Remove User from TeamTool to remove a user from a Pushover for Teams organization.
Validate User or GroupTool to validate a Pushover user or group key for deliverability.

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 Pushover account and project
  • Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Pushover

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 Pushover 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 pushover_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=["pushover"],
    )

    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 Pushover actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Pushover 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, pushover)
  • 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 Pushover 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 Pushover 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 Pushover

Run the agent

npx ts-node llamaindex-agent.ts

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

Complete Code

Here's the complete code to get you started with Pushover 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=["pushover"],
    )

    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 Pushover actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Pushover 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 Pushover to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:
  • Tool Router dynamically exposes Pushover 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 Pushover MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Pushover MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Pushover MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Pushover MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Pushover MCP with Claude Cowork

Codex logo

Codex

Use Pushover MCP with Codex

OpenClaw logo

OpenClaw

Use Pushover MCP with OpenClaw

Hermes logo

Hermes

Use Pushover MCP with Hermes

CLI logo

CLI

Use Pushover MCP with CLI

Google ADK logo

Google ADK

Use Pushover MCP with Google ADK

LangChain logo

LangChain

Use Pushover MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Pushover MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Pushover MCP with Mastra AI

CrewAI logo

CrewAI

Use Pushover MCP with CrewAI

FAQ

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

With a standalone Pushover MCP server, the agents and LLMs can only access a fixed set of Pushover tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Pushover 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 Pushover tools.

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

Yes, absolutely. You can configure which Pushover 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 Pushover 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↗