How to integrate Servicem8 MCP with Pydantic AI

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Servicem8 Logo
Pydantic AI Logo
divider

Introduction

This guide walks you through connecting Servicem8 to Pydantic AI using the Composio tool router. By the end, you'll have a working Servicem8 agent that can create a new job for a plumbing callout, list all clients with overdue invoices, add a payment note to job 12345, show all available job document templates through natural language commands.

This guide will help you understand how to give your Pydantic AI agent real control over a Servicem8 account through Composio's Servicem8 MCP server.

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

TL;DR

Here's what you'll learn:
  • How to set up your Composio API key and User ID
  • How to create a Composio Tool Router session for Servicem8
  • How to attach an MCP Server to a Pydantic AI agent
  • How to stream responses and maintain chat history
  • How to build a simple REPL-style chat interface to test your Servicem8 workflows

What is Pydantic AI?

Pydantic AI is a Python framework for building AI agents with strong typing and validation. It leverages Pydantic's data validation capabilities to create robust, type-safe AI applications.

Key features include:

  • Type Safety: Built on Pydantic for automatic data validation
  • MCP Support: Native support for Model Context Protocol servers
  • Streaming: Built-in support for streaming responses
  • Async First: Designed for async/await patterns

What is the Servicem8 MCP server, and what's possible with it?

The Servicem8 MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Servicem8 account. It provides structured and secure access to your job management system, so your agent can perform actions like creating jobs, managing notes and payments, listing clients, and retrieving templates on your behalf.

  • Job creation and management: Instruct your agent to create new jobs, add detailed job information, or update records, streamlining field service operations.
  • Automated note handling: Have your agent attach important notes to jobs or remove outdated notes to keep job records clean and up-to-date.
  • Payment processing and tracking: Let your agent record new job payments or archive payment records, ensuring accurate and timely invoicing.
  • Comprehensive client and asset retrieval: Ask your agent to pull complete lists of clients and assets for reporting, integrations, or inventory management.
  • Template and form discovery: Fetch available document templates and forms so your agent can prepare job paperwork or gather required information efficiently.

Supported Tools & Triggers

Tools
ServiceM8 Create Job NoteTool to create a new job note in servicem8.
ServiceM8 Create Job PaymentTool to create a new job payment in servicem8.
Create a new JobTool to create a new job in servicem8.
Delete Job NoteTool to delete a specific job note.
ServiceM8 Delete Job PaymentTool to delete (archive) a specific job payment by its uuid.
List All AssetsTool to list all servicem8 assets.
List All ClientsTool to list all servicem8 clients.
List All Document TemplatesTool to list document templates.
List All FormsTool to list all servicem8 forms.
List All Job NotesTool to list all job notes in servicem8.
List All Job QueuesTool to list all job queues in servicem8.
List All JobsTool to list all jobs.
List All LocationsTool to list all servicem8 locations.
List All MaterialsTool to list all materials.
List All TasksTool to list all tasks in a servicem8 account.
Retrieve ServiceM8 ClientTool to retrieve details of a specific client by its uuid.
Retrieve FormTool to retrieve details of a specific form by its uuid.
Retrieve JobTool to retrieve details of a specific job by its uuid.
Retrieve Job ActivityTool to retrieve details of a specific job activity by its uuid.
Retrieve Job NoteTool to retrieve details of a specific job note by its uuid.
Retrieve Job PaymentTool to retrieve details of a specific job payment by its uuid.
Retrieve Job QueueTool to retrieve details of a specific job queue by its uuid.
Retrieve LocationTool to retrieve details of a specific location by its uuid.
Retrieve ServiceM8 MaterialTool to retrieve details of a specific material by its uuid.
Retrieve Staff MemberTool to retrieve details of a specific staff member by their uuid.
ServiceM8 Create JobTool to create a new job in servicem8.
Update a ServiceM8 Job NoteTool to update details of an existing job note.
ServiceM8 Update Job PaymentTool to update details of an existing job payment.

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

What is Tool Router?

Composio's Tool Router 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 Tool Router

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

How the Tool Router works

The Tool Router 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 starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account with an active API key
  • Basic familiarity with Python and async programming

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 pydantic-ai python-dotenv

Install the required libraries.

What's happening:

  • composio connects your agent to external SaaS tools like Servicem8
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your agent to Composio's API
  • USER_ID associates your session with your account for secure tool access
  • OPENAI_API_KEY to access OpenAI LLMs

Import dependencies

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()
What's happening:
  • We load environment variables and import required modules
  • Composio manages connections to Servicem8
  • MCPServerStreamableHTTP connects to the Servicem8 MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant

Create a Tool Router Session

python
async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Servicem8
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["servicem8"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")
What's happening:
  • We're creating a Tool Router session that gives your agent access to Servicem8 tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use

Initialize the Pydantic AI Agent

python
# Attach the MCP server to a Pydantic AI Agent
servicem8_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[servicem8_mcp],
    instructions=(
        "You are a Servicem8 assistant. Use Servicem8 tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Servicem8 endpoint
  • The agent uses GPT-5 to interpret user commands and perform Servicem8 operations
  • The instructions field defines the agent's role and behavior

Build the chat interface

python
# Simple REPL with message history
history = []
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to help you with Servicem8.\n")

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", flush=True)

    async with agent.run_stream(user_input, message_history=history) as stream_result:
        collected_text = ""
        async for chunk in stream_result.stream_output():
            text_piece = None
            if isinstance(chunk, str):
                text_piece = chunk
            elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                text_piece = chunk.delta
            elif hasattr(chunk, "text"):
                text_piece = chunk.text
            if text_piece:
                collected_text += text_piece
        result = stream_result

    print(f"Agent: {collected_text}\n")
    history = result.all_messages()
What's happening:
  • The agent reads input from the terminal and streams its response
  • Servicem8 API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns

Run the application

python
if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • The asyncio loop launches the agent and keeps it running until you exit

Complete Code

Here's the complete code to get you started with Servicem8 and Pydantic AI:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()

async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Servicem8
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["servicem8"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")

    # Attach the MCP server to a Pydantic AI Agent
    servicem8_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[servicem8_mcp],
        instructions=(
            "You are a Servicem8 assistant. Use Servicem8 tools to help users "
            "with their requests. Ask clarifying questions when needed."
        ),
    )

    # Simple REPL with message history
    history = []
    print("Chat started! Type 'exit' or 'quit' to end.\n")
    print("Try asking the agent to help you with Servicem8.\n")

    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", flush=True)

        async with agent.run_stream(user_input, message_history=history) as stream_result:
            collected_text = ""
            async for chunk in stream_result.stream_output():
                text_piece = None
                if isinstance(chunk, str):
                    text_piece = chunk
                elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                    text_piece = chunk.delta
                elif hasattr(chunk, "text"):
                    text_piece = chunk.text
                if text_piece:
                    collected_text += text_piece
            result = stream_result

        print(f"Agent: {collected_text}\n")
        history = result.all_messages()

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

Conclusion

You've built a Pydantic AI agent that can interact with Servicem8 through Composio's Tool Router. With this setup, your agent can perform real Servicem8 actions through natural language. You can extend this further by:
  • Adding other toolkits like Gmail, HubSpot, or Salesforce
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows (for example, Gmail + Servicem8 for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.

How to build Servicem8 MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Servicem8 MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Servicem8 MCP with Claude Agent SDK

Google ADK

Google ADK

Use Servicem8 MCP with Google ADK

LangChain

LangChain

Use Servicem8 MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Servicem8 MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Servicem8 MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Servicem8 MCP with LlamaIndex

CrewAI

CrewAI

Use Servicem8 MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Servicem8 MCP?

With a standalone Servicem8 MCP server, the agents and LLMs can only access a fixed set of Servicem8 tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Servicem8 and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with Pydantic AI?

Yes, you can. Pydantic AI 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 Servicem8 tools.

Can I manage the permissions and scopes for Servicem8 while using Tool Router?

Yes, absolutely. You can configure which Servicem8 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 Servicem8 data and credentials are handled as safely as possible.

Used by agents from

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

Book a call↗Get started for free