How to integrate Jobnimbus MCP with CrewAI

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Jobnimbus Logo
CrewAI Logo
divider

Introduction

This guide walks you through connecting Jobnimbus to CrewAI using the Composio tool router. By the end, you'll have a working Jobnimbus agent that can list all open tasks for this week, create a new material order for a contact, fetch details for contact by name, add a custom file attachment type through natural language commands.

This guide will help you understand how to give your CrewAI agent real control over a Jobnimbus account through Composio's Jobnimbus 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:
  • Get a Composio API key and configure your Jobnimbus connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for Jobnimbus
  • Build a conversational loop where your agent can execute Jobnimbus 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 Jobnimbus MCP server, and what's possible with it?

The Jobnimbus MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Jobnimbus account. It provides structured and secure access to your CRM and project management data, so your agent can perform actions like managing contacts, scheduling tasks, creating locations, and retrieving account information on your behalf.

  • Contact management and lookup: Instantly create new contacts or fetch full details and lists of existing contacts for streamlined project tracking and reporting.
  • Task scheduling and tracking: Direct your agent to create and assign tasks, helping teams stay organized and on top of project to-dos.
  • Location and job site creation: Quickly add new locations to your Jobnimbus account, ensuring every job and address is properly logged for future reference.
  • Material order and workflow automation: Let your agent place material orders for jobs and update workflow statuses to keep projects moving smoothly from lead to completion.
  • Account and attachment management: Retrieve account settings or pull file attachments by ID, supporting seamless document handling and system configuration.

Supported Tools & Triggers

Tools
Create LocationTool to create a new location in jobnimbus.
Get Activity by IDTool to retrieve a specific activity by its id.
Get Contact by IDTool to retrieve a contact by id.
List ContactsTool to list all contacts.
Create File Attachment TypeTool to create a new file attachment type.
Create Material OrderTool to create a new material order (v2).
Create TaskTool to create a new task.
Create Workflow StatusTool to create a new status in an existing workflow.
Get File Attachment by IDTool to retrieve a specific file attachment's raw content by id.
Get Account SettingsTool to retrieve account-wide settings (workflows, types, sources).
Update ContactTool to update an existing contact.
List TasksTool to list all tasks.
List ActivitiesTool to retrieve all activities.
List InvoicesTool to list all invoices (v2).
List Material OrdersTool to list all material orders (v2).
List PaymentsTool to retrieve payments list with optional filters.
List ProductsTool to list all products.
List Work OrdersTool to retrieve all work orders (v2).
Get Product by IDTool to retrieve a specific product by id (v2).
Update TaskTool to update an existing task.
Get Units of MeasureTool to retrieve list of supported units of measure.

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 and API key
  • A Jobnimbus connection authorized in Composio
  • An OpenAI API key for the CrewAI LLM
  • Basic familiarity with Python

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 crewai crewai-tools python-dotenv
What's happening:
  • composio connects your agent to Jobnimbus via MCP
  • crewai provides Agent, Task, Crew, and LLM primitives
  • crewai-tools includes MCP helpers
  • python-dotenv loads environment variables from .env

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

Import dependencies

python
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional import if you plan to adapt tools
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()
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 Jobnimbus MCP URL

Create a Composio Tool Router session for Jobnimbus

python
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
    user_id=os.getenv("USER_ID"),
    toolkits=["jobnimbus"],
)
url = session.mcp.url
What's happening:
  • You create a Jobnimbus only session through Composio
  • Composio returns an MCP HTTP URL that exposes Jobnimbus tools

Configure the LLM

python
llm = LLM(
    model="gpt-5-mini",
    api_key=os.getenv("OPENAI_API_KEY"),
)
What's happening:
  • CrewAI will call this LLM for planning and responses
  • You can swap in a different model if needed

Attach the MCP server and create the agent

python
toolkit_agent = Agent(
    role="Jobnimbus Assistant",
    goal="Help users interact with Jobnimbus through natural language commands",
    backstory=(
        "You are an expert assistant with access to Jobnimbus tools. "
        "You can perform various Jobnimbus operations on behalf of the user."
    ),
    mcps=[
        MCPServerHTTP(
            url=url,
            streamable=True,
            cache_tools_list=True,
            headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
        ),
    ],
    llm=llm,
    verbose=True,
    max_iter=10,
)
What's happening:
  • MCPServerHTTP connects the agent to the Jobnimbus MCP endpoint
  • cache_tools_list saves a tools catalog for faster subsequent runs
  • verbose helps you see what the agent is doing

Add a REPL loop with Task and Crew

python
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to perform Jobnimbus operations.\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"Based on the conversation history:\n{conversation_context}\n\n"
            f"Current user request: {user_input}\n\n"
            f"Please help the user with their Jobnimbus related request."
        ),
        expected_output="A helpful response addressing the user's request",
        agent=toolkit_agent,
    )

    crew = Crew(
        agents=[toolkit_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:
  • You build a simple chat loop and keep a running context
  • Each user turn becomes a Task handled by the same agent
  • Crew executes the task and returns a response

Run the application

python
if __name__ == "__main__":
    main()
What's happening:
  • Standard Python entry point so you can run python crewai_jobnimbus_agent.py

Complete Code

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

python
# file: crewai_jobnimbus_agent.py
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()

def main():
    # Initialize Composio and create a Jobnimbus session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["jobnimbus"],
    )
    url = session.mcp.url

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

    # Create Jobnimbus assistant agent
    toolkit_agent = Agent(
        role="Jobnimbus Assistant",
        goal="Help users interact with Jobnimbus through natural language commands",
        backstory=(
            "You are an expert assistant with access to Jobnimbus tools. "
            "You can perform various Jobnimbus operations on behalf of the user."
        ),
        mcps=[
            MCPServerHTTP(
                url=url,
                streamable=True,
                cache_tools_list=True,
                headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
            ),
        ],
        llm=llm,
        verbose=True,
        max_iter=10,
    )

    print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
    print("Try asking the agent to perform Jobnimbus operations.\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"Based on the conversation history:\n{conversation_context}\n\n"
                f"Current user request: {user_input}\n\n"
                f"Please help the user with their Jobnimbus related request."
            ),
            expected_output="A helpful response addressing the user's request",
            agent=toolkit_agent,
        )

        crew = Crew(
            agents=[toolkit_agent],
            tasks=[task],
            verbose=False,
        )

        result = crew.kickoff()
        response = str(result)

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

if __name__ == "__main__":
    main()

Conclusion

You now have a CrewAI agent connected to Jobnimbus through Composio's Tool Router. The agent can perform Jobnimbus 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

How to build Jobnimbus MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Jobnimbus MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Jobnimbus MCP with Claude Agent SDK

Google ADK

Google ADK

Use Jobnimbus MCP with Google ADK

LangChain

LangChain

Use Jobnimbus MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Jobnimbus MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Jobnimbus MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Jobnimbus MCP with LlamaIndex

FAQ

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

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

Can I use Tool Router MCP with CrewAI?

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 Jobnimbus tools.

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

Yes, absolutely. You can configure which Jobnimbus 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 Jobnimbus 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