How to integrate Desktime MCP with CrewAI

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

Introduction

This guide walks you through connecting Desktime to CrewAI using the Composio tool router. By the end, you'll have a working Desktime agent that can list all active projects with tasks, get today's time tracked for each employee, start timing work on 'client website redesign', show app usage for employee 12345 yesterday through natural language commands.

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

The Desktime MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Desktime account. It provides structured and secure access to your time tracking, project management, and productivity data, so your agent can perform actions like tracking work hours, managing projects, analyzing employee productivity, and reporting on team activities on your behalf.

  • Automated project and task management: Create new projects, assign optional starter tasks, and retrieve a comprehensive list of active company projects for streamlined organization.
  • Employee and company insights: Instantly fetch detailed company account info, list all employees with their roles and statuses, and access individual employee data for better workforce visibility.
  • Time tracking control: Start or stop tracking work on specific projects and tasks, enabling hands-free, accurate logging of work sessions and project contributions.
  • Productivity and app usage analysis: Retrieve employee project assignments and application usage data to monitor work habits and identify productivity trends across your team.
  • API health and connectivity checks: Use built-in API ping tools to verify Desktime API availability and ensure uninterrupted agent operations.

Supported Tools & Triggers

Tools
Create Project with Optional TaskTool to create a new project with an optional initial task.
Get Account DetailsTool to retrieve detailed information about the authenticated user's company account.
Get All Company EmployeesTool to list all employees in the company, including their roles and statuses.
Get Employee DataTool to fetch data for all employees within the company.
Get Employee ProjectsTool to retrieve information about projects assigned to employees, including project names, durations, and statuses.
Get Employee Projects and AppsTool to retrieve an employee's tracked projects and application usage.
Get Projects ListTool to retrieve all active projects for the company, including related tasks.
Ping DeskTime APITool to check the api's availability and confirm the service is operational.
Start Project TaskTool to start tracking time for a specified project and optional task.
Stop Project TaskTool to stop tracking time for a specified project and optional task.

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 Desktime 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 Desktime 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 Desktime MCP URL

Create a Composio Tool Router session for Desktime

python
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
    user_id=os.getenv("USER_ID"),
    toolkits=["desktime"],
)
url = session.mcp.url
What's happening:
  • You create a Desktime only session through Composio
  • Composio returns an MCP HTTP URL that exposes Desktime 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="Desktime Assistant",
    goal="Help users interact with Desktime through natural language commands",
    backstory=(
        "You are an expert assistant with access to Desktime tools. "
        "You can perform various Desktime 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 Desktime 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 Desktime 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 Desktime 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_desktime_agent.py

Complete Code

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

python
# file: crewai_desktime_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 Desktime session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["desktime"],
    )
    url = session.mcp.url

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

    # Create Desktime assistant agent
    toolkit_agent = Agent(
        role="Desktime Assistant",
        goal="Help users interact with Desktime through natural language commands",
        backstory=(
            "You are an expert assistant with access to Desktime tools. "
            "You can perform various Desktime 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 Desktime 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 Desktime 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 Desktime through Composio's Tool Router. The agent can perform Desktime 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 Desktime MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Desktime MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Desktime MCP with Claude Agent SDK

Google ADK

Google ADK

Use Desktime MCP with Google ADK

LangChain

LangChain

Use Desktime MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Desktime MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Desktime MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Desktime MCP with LlamaIndex

FAQ

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

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

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

Yes, absolutely. You can configure which Desktime 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 Desktime 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