SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Servicem8 MCP with CrewAI

Connect CrewAI to Servicem8 MCP. Create a new job for a plumbing callout, list all clients with overdue invoices, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Servicem8 logoServicem8
Oauth2

Servicem8 is a field service management platform for scheduling jobs, quoting, and invoicing. It helps businesses track real-time job status and empower mobile staff in the field.

61 Tools

Introduction

This guide walks you through connecting Servicem8 to CrewAI using the Composio tool router. By the end, you'll have a working Servicem8 agent that can create and update jobs, manage clients and contacts, add job notes and materials, record job payments, and track tasks through natural language commands.

This guide will help you understand how to give your CrewAI 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.

Also integrate Servicem8 with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexPydantic AIAutoGen

TL;DR

Here's what you'll learn:
  • Get a Composio API key and configure your Servicem8 connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for Servicem8
  • Build a conversational loop where your agent can execute Servicem8 operations

What is CrewAI?

CrewAI is a powerful framework for building multi-agent AI systems. It provides primitives for defining agents with specific roles, creating tasks, and orchestrating workflows through crews.

Key features include:

  • Agent Roles: Define specialized agents with specific goals and backstories
  • Task Management: Create tasks with clear descriptions and expected outputs
  • Crew Orchestration: Combine agents and tasks into collaborative workflows
  • MCP Integration: Connect to external tools through Model Context Protocol

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.

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

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account and API key
  • A Servicem8 connection authorized in Composio
  • An OpenAI API key for the CrewAI LLM
  • Basic familiarity with Python
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 crewai crewai-tools[mcp] python-dotenv
What's happening:
  • composio connects your agent to Servicem8 via MCP
  • crewai provides Agent, Task, Crew, and LLM primitives
  • crewai-tools[mcp] includes MCP helpers
  • python-dotenv loads environment variables from .env
4

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_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates with Composio
  • USER_ID scopes the session to your account
  • OPENAI_API_KEY lets CrewAI use your chosen OpenAI model
5

Import dependencies

python
import os
from composio import Composio
from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
import dotenv

dotenv.load_dotenv()

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

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")
What's happening:
  • CrewAI classes define agents and tasks, and run the workflow
  • MCPServerHTTP connects the agent to an MCP endpoint
  • Composio will give you a short lived Servicem8 MCP URL
6

Create a Composio Tool Router session for Servicem8

python
composio_client = Composio(api_key=COMPOSIO_API_KEY)
session = composio_client.create(user_id=COMPOSIO_USER_ID, toolkits=["servicem8"])

url = session.mcp.url
What's happening:
  • You create a Servicem8 only session through Composio
  • Composio returns an MCP HTTP URL that exposes Servicem8 tools
7

Initialize the MCP Server

python
server_params = {
    "url": url,
    "transport": "streamable-http",
    "headers": {"x-api-key": COMPOSIO_API_KEY},
}

with MCPServerAdapter(server_params) as tools:
    agent = Agent(
        role="Search Assistant",
        goal="Help users search the internet effectively",
        backstory="You are a helpful assistant with access to search tools.",
        tools=tools,
        verbose=False,
        max_iter=10,
    )
What's Happening:
  • Server Configuration: The code sets up connection parameters including the MCP server URL, streamable HTTP transport, and Composio API key authentication.
  • MCP Adapter Bridge: MCPServerAdapter acts as a context manager that converts Composio MCP tools into a CrewAI-compatible format.
  • Agent Setup: Creates a CrewAI Agent with a defined role (Search Assistant), goal (help with internet searches), and access to the MCP tools.
  • Configuration Options: The agent includes settings like verbose=False for clean output and max_iter=10 to prevent infinite loops.
  • Dynamic Tool Usage: Once created, the agent automatically accesses all Composio Search tools and decides when to use them based on user queries.
8

Create a CLI Chatloop and define the Crew

python
print("Chat started! Type 'exit' or 'quit' to end.\n")

conversation_context = ""

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

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

    if not user_input:
        continue

    conversation_context += f"\nUser: {user_input}\n"
    print("\nAgent is thinking...\n")

    task = Task(
        description=(
            f"Conversation history:\n{conversation_context}\n\n"
            f"Current request: {user_input}"
        ),
        expected_output="A helpful response addressing the user's request",
        agent=agent,
    )

    crew = Crew(agents=[agent], tasks=[task], verbose=False)
    result = crew.kickoff()
    response = str(result)

    conversation_context += f"Agent: {response}\n"
    print(f"Agent: {response}\n")
What's Happening:
  • Interactive CLI Setup: The code creates an infinite loop that continuously prompts for user input and maintains the entire conversation history in a string variable.
  • Input Validation: Empty inputs are ignored to prevent processing blank messages and keep the conversation clean.
  • Context Building: Each user message is appended to the conversation context, which preserves the full dialogue history for better agent responses.
  • Dynamic Task Creation: For every user input, a new Task is created that includes both the full conversation history and the current request as context.
  • Crew Execution: A Crew is instantiated with the agent and task, then kicked off to process the request and generate a response.
  • Response Management: The agent's response is converted to a string, added to the conversation context, and displayed to the user, maintaining conversational continuity.

Complete Code

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

python
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter
from composio import Composio
from dotenv import load_dotenv
import os

load_dotenv()

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

if not GOOGLE_API_KEY:
    raise ValueError("GOOGLE_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.")

# Initialize Composio and create a session
composio = Composio(api_key=COMPOSIO_API_KEY)
session = composio.create(
    user_id=COMPOSIO_USER_ID,
    toolkits=["servicem8"],
)
url = session.mcp.url

# Configure LLM
llm = LLM(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY"),
)

server_params = {
    "url": url,
    "transport": "streamable-http",
    "headers": {"x-api-key": COMPOSIO_API_KEY},
}

with MCPServerAdapter(server_params) as tools:
    agent = Agent(
        role="Search Assistant",
        goal="Help users with internet searches",
        backstory="You are an expert assistant with access to Composio Search tools.",
        tools=tools,
        llm=llm,
        verbose=False,
        max_iter=10,
    )

    print("Chat started! Type 'exit' or 'quit' to end.\n")

    conversation_context = ""

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

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

        if not user_input:
            continue

        conversation_context += f"\nUser: {user_input}\n"
        print("\nAgent is thinking...\n")

        task = Task(
            description=(
                f"Conversation history:\n{conversation_context}\n\n"
                f"Current request: {user_input}"
            ),
            expected_output="A helpful response addressing the user's request",
            agent=agent,
        )

        crew = Crew(agents=[agent], tasks=[task], verbose=False)
        result = crew.kickoff()
        response = str(result)

        conversation_context += f"Agent: {response}\n"
        print(f"Agent: {response}\n")

Conclusion

You now have a CrewAI agent connected to Servicem8 through Composio's Tool Router. The agent can perform Servicem8 operations through natural language commands.

Next steps:

  • Add role-specific instructions to customize agent behavior
  • Plug in more toolkits for multi-app workflows
  • Chain tasks for complex multi-step operations
TOOLS

Supported Tools

Every Servicem8 action and event your agent gets out of the box.

Create ServiceM8 Client

Create a ServiceM8 client company and retrieve its saved record.

Create Company Contact

Create a contact for a ServiceM8 client company and return its UUID.

Create Job Activity

Create a scheduled or recorded ServiceM8 job activity and return its UUID.

Create Job Checklist

Create a ServiceM8 job checklist item and return its UUID.

Create Job Contact

Add a contact to a ServiceM8 job and return its created UUID.

Add Job Material

Add a material line to a ServiceM8 job and return its created UUID.

ServiceM8 Create Job Note

Create a new job note in ServiceM8.

ServiceM8 Create Job Payment

Tool to create a new job payment in ServiceM8.

Create a new Job

Create a new ServiceM8 job and retrieve its saved record.

Create Material

Create a ServiceM8 material catalog record and return its UUID.

ServiceM8 Create Task

Create a ServiceM8 task, optionally related to another ServiceM8 record.

Delete Custom Field

Delete a custom field in ServiceM8 by its UUID.

Delete Job Activity

Archive a ServiceM8 job activity by UUID.

Delete Job Note

Deletes (archives) a job note in ServiceM8 by its UUID.

Delete Job Payment

Archives (soft-deletes) a job payment record in ServiceM8 by its UUID.

List All Assets

Tool to list all ServiceM8 assets.

List All Clients

Tool to list all ServiceM8 clients.

List All Document Templates

Tool to list document templates.

List All Forms

List ServiceM8 form templates, optionally using an OData-style filter to narrow the results.

List All Job Notes

List all job notes from ServiceM8.

List All Job Queues

List all job queues in ServiceM8.

List All Jobs

Tool to list all jobs.

List All Locations

Lists all ServiceM8 locations.

List All Materials

List ServiceM8 materials, including products, labour rates and inventory items, with optional filtering; requires the 'read_inventory' OAuth scope.

List All Tasks

Retrieves all tasks from a ServiceM8 account with optional filtering and cursor-based pagination.

List Attachments

List ServiceM8 attachment metadata with filtering and cursor pagination.

List Company Contacts

List company contacts, optionally narrowed by an OData filter.

List Form Responses

List submitted ServiceM8 form responses with filtering and pagination.

List Job Activities

List and filter ServiceM8 job activities with cursor pagination.

List Job Allocations

List ServiceM8 job allocations, optionally filtered by public fields.

List Job Categories

List job categories, optionally narrowed by an OData filter.

List Job Checklists

List ServiceM8 job checklist items with filtering and cursor pagination.

List Job Contacts

List contacts linked to ServiceM8 jobs, with filtering and cursor pagination.

List Job Materials

List material assignments on ServiceM8 jobs.

List Job Payments

List, filter, and cursor-page ServiceM8 job payments.

List Staff Members

List staff members, optionally narrowed by an OData filter.

List Vendors

List vendor accounts, optionally narrowed by an OData filter.

Retrieve ServiceM8 Client

Tool to retrieve details of a specific client by its UUID.

Get Company Contact

Retrieve one ServiceM8 company contact by its UUID.

Retrieve Form

Retrieve details of a specific form template by its UUID.

Retrieve Job

Tool to retrieve details of a specific job by its UUID.

Retrieve Job Activity

Tool to retrieve details of a specific job activity by its UUID.

Get Job Contact

Retrieve one ServiceM8 job contact by its UUID.

Get Job Material

Retrieve one ServiceM8 job material line item by its UUID.

Retrieve Job Note

Retrieve the full details of a specific job note by its UUID.

Retrieve Job Payment

Retrieve a specific job payment record from ServiceM8 by its UUID.

Retrieve Job Queue

Tool to retrieve details of a specific job queue by its UUID.

Retrieve Location

Retrieve a ServiceM8 location by UUID, including available address, geographic coordinates, contact phone number, and active status.

Retrieve ServiceM8 Material

Retrieve detailed information about a specific material/product/service by its UUID.

Retrieve Staff Member

Tool to retrieve details of a specific staff member by their UUID.

Update ServiceM8 Client

Update a ServiceM8 client by UUID, requiring the client name, and retrieve the saved record.

Update Company Contact

Partially update a company contact by UUID and retrieve the saved record.

Update ServiceM8 Job

Update a ServiceM8 job by UUID, requiring a job status, and retrieve the saved record.

Update Job Activity

Update a known job activity and return it.

Update Job Contact

Update selected fields on a ServiceM8 job contact and return the saved record.

Update Job Material

Update an existing material line assigned to a ServiceM8 job.

Update a ServiceM8 Job Note

Tool to update details of an existing job note.

Update Job Payment

Update an existing job payment record in ServiceM8.

Update ServiceM8 Job Queue

Update a ServiceM8 job queue and return its saved provider record.

Update ServiceM8 Material

Update an inventory material by UUID, requiring its name, and return its saved provider record.

ServiceM8 Update Task

Update a ServiceM8 task by UUID, requiring its name, and return the saved record.

FRAMEWORKS

How to build Servicem8 MCP Agent with another framework

Claude Code logo

Claude Code

Use Servicem8 MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Servicem8 MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Servicem8 MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Servicem8 MCP with Claude Agent SDK

Codex logo

Codex

Use Servicem8 MCP with Codex

OpenClaw logo

OpenClaw

Use Servicem8 MCP with OpenClaw

Hermes logo

Hermes

Use Servicem8 MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Servicem8 MCP with Atomic Agent

Google ADK logo

Google ADK

Use Servicem8 MCP with Google ADK

LangChain logo

LangChain

Use Servicem8 MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Servicem8 MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Servicem8 MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Servicem8 MCP with LlamaIndex

Pydantic AI logo

Pydantic AI

Use Servicem8 MCP with Pydantic AI

AutoGen logo

AutoGen

Use Servicem8 MCP with AutoGen

FAQ

Frequently asked questions

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.

Yes, you can. CrewAI 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.

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.

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.

Start with Servicem8.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Servicem8 tool your agent needs.Free to start.

Start building