How to integrate Worksnaps MCP with CrewAI

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

Introduction

This guide walks you through connecting Worksnaps to CrewAI using the Composio tool router. By the end, you'll have a working Worksnaps agent that can show my total hours logged this week, list all tasks for project alpha, create a new project for client onboarding, get my current project assignments through natural language commands.

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

The Worksnaps MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Worksnaps account. It provides structured and secure access to your time tracking and project data, so your agent can perform actions like tracking project hours, managing tasks, retrieving detailed reports, and accessing user assignments on your behalf.

  • Project and task management: Direct your agent to create new projects, add tasks, or delete tasks from specific projects for streamlined workflow organization.
  • Comprehensive project reporting: Request detailed time tracking reports for individual projects, including daily summaries and custom date ranges.
  • Account and assignment insights: Let your agent fetch account details and list all user assignments to see which projects you're working on or managing.
  • Quick project overview retrieval: Ask the agent to list all accessible projects or view detailed information about any project with just a prompt.
  • Task detail and status checks: Retrieve details for any task within a project, so you can stay on top of progress and workload effortlessly.

Supported Tools & Triggers

Tools
Create ProjectTool to create a new project in worksnaps.
Create taskTool to create a new task in a specified project.
Delete TaskTool to delete a task from a project.
Get Project DetailsTool to retrieve details of a specific project.
Get Project ReportTool to retrieve a project's time tracking report.
Get ProjectsTool to retrieve a paginated list of projects.
Get Task DetailsTool to retrieve details of a specific task within a project.
Get Project TasksTool to retrieve tasks for a specific project.
Get User AccountTool to retrieve information about a specific user account.
Get User AssignmentsTool to retrieve a list of all user assignments for the authenticated user.
Get UsersTool to retrieve a list of all users.
Update ProjectTool to update an existing project.
Update TaskTool to update details of an existing task.
Update User AccountTool to update information for a specific user account.

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 Worksnaps 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 Worksnaps 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 Worksnaps MCP URL

Create a Composio Tool Router session for Worksnaps

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

Complete Code

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

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

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

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

OpenAI Agents SDK

OpenAI Agents SDK

Use Worksnaps MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Worksnaps MCP with Claude Agent SDK

Google ADK

Google ADK

Use Worksnaps MCP with Google ADK

LangChain

LangChain

Use Worksnaps MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Worksnaps MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Worksnaps MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Worksnaps MCP with LlamaIndex

FAQ

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

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

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

Yes, absolutely. You can configure which Worksnaps 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 Worksnaps 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