SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Pingdom MCP with Autogen

Connect Autogen to Pingdom MCP. List all uptime checks for your sites, show account credit and api usage left, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Pingdom logoPingdom
Api Key

Pingdom is a web performance monitoring service for websites, servers, and applications. It helps you track uptime, performance, and get alerts when things go down.

13 Tools

Introduction

This guide walks you through connecting Pingdom to AutoGen using the Composio tool router. By the end, you'll have a working Pingdom agent that can list uptime and transaction checks, view maintenance windows, look up alert contacts and teams, and check your credits through natural language commands.

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

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

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Pingdom with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKGrok BotCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIPydantic AI

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 Pingdom
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Pingdom tools
  • Run a live chat loop where you ask the agent to perform Pingdom 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 Pingdom MCP server, and what's possible with it?

The Pingdom MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Pingdom account. It provides structured and secure access to your monitoring data, so your agent can perform actions like retrieving uptime checks, managing alerts and contacts, viewing maintenance windows, and running immediate availability tests on your behalf.

  • Comprehensive uptime and check monitoring: Instantly fetch overviews of all your uptime checks, retrieve details for specific checks, and keep tabs on your website and server performance.
  • Alert action and contact management: Ask your agent to list all alerting actions, fetch contacts, or get detailed notification configurations for each contact in your Pingdom account.
  • Maintenance window tracking: Let your agent list and filter scheduled maintenance windows and occurrences, helping you plan downtime and track monitoring exceptions.
  • Immediate single-site checks: Perform real-time availability or performance tests on any host or URL directly from your agent, using specific probes and check types.
  • Reference data and credits insight: Retrieve essential reference lists (like time zones, probes, and contact types) and check your API credit and rate-limit status to stay informed and proactive.

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

Step by step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Pingdom account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
2

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.
3

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 Pingdom via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

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 Pingdom connections to use
5

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 Pingdom session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["pingdom"]
    )
    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 Pingdom tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

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
7

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 Pingdom assistant agent with MCP tools
    agent = AssistantAgent(
        name="pingdom_assistant",
        description="An AI assistant that helps with Pingdom 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 Pingdom tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Pingdom 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 Pingdom 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 Pingdom 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 Pingdom session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["pingdom"]
    )
    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 Pingdom assistant agent with MCP tools
        agent = AssistantAgent(
            name="pingdom_assistant",
            description="An AI assistant that helps with Pingdom 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 Pingdom 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 Pingdom 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 Pingdom, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

Every Pingdom action and event your agent gets out of the box.

Get Pingdom Alert Actions

Requests generated alert actions for the Pingdom account, with check, user, channel and time parameters.

Get Checks List

Retrieves a list of all uptime/monitoring checks configured in Pingdom with optional filtering and pagination.

Get Contact Details

Retrieves comprehensive details of a specific Pingdom alerting contact by ID, including all configured notification methods (email, SMS), team memberships, contact type, and pause status.

Get Contacts

Retrieves alerting contacts and their notification targets from Pingdom.

Get Credits

Retrieves Pingdom account credits and resource usage, including check and SMS information.

List Maintenance Occurrences

Lists Pingdom maintenance occurrences, with optional time-range and maintenance window ID parameters.

Get Maintenance Windows

Lists a user's Pingdom maintenance windows, with optional pagination and time-range parameters.

Get Probes

Lists Pingdom probe servers used for uptime and transaction checks, with location, IP address and availability information.

Get Reference Data

Retrieves Pingdom reference data including regions, timezones, datetime formats, number formats, and countries.

Get Single Check

Perform a single on-demand Pingdom check against a target host.

Get Team Details

Tool to fetch detailed information for a specific alerting team.

Get Teams

Tool to retrieve all alerting teams and their members.

Get TMS Transaction Checks List

Lists Pingdom transaction (TMS) checks in a paginated overview, including their IDs, names, types and statuses.

FRAMEWORKS

How to build Pingdom MCP Agent with another framework

Claude Code logo

Claude Code

Use Pingdom MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Pingdom MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Pingdom MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Pingdom MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Pingdom MCP with Grok Bot

Codex logo

Codex

Use Pingdom MCP with Codex

OpenClaw logo

OpenClaw

Use Pingdom MCP with OpenClaw

Hermes logo

Hermes

Use Pingdom MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Pingdom MCP with Atomic Agent

Google ADK logo

Google ADK

Use Pingdom MCP with Google ADK

LangChain logo

LangChain

Use Pingdom MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Pingdom MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Pingdom MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Pingdom MCP with LlamaIndex

CrewAI logo

CrewAI

Use Pingdom MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Pingdom MCP with Pydantic AI

FAQ

Frequently asked questions

Start with Pingdom.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Pingdom tool your agent needs.Free to start.

Start building