SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Everhour MCP with Autogen

Connect Autogen to Everhour MCP. List all clients for this workspace, retrieve expense categories for new report, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Everhour logoEverhour
Api Key

Everhour is a time tracking and expense management platform for teams and individuals. Gain insight into hours, costs, and budgets for smarter planning and resource allocation.

51 Tools

Introduction

This guide walks you through connecting Everhour to AutoGen using the Composio tool router. By the end, you'll have a working Everhour agent that can start timers, clock in and out, manage clients and projects, review timecards and timesheets, and list expenses and invoices through natural language commands.

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

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

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Everhour with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKGrok BotCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIPydantic AI

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Everhour
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Everhour tools
  • Run a live chat loop where you ask the agent to perform Everhour operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

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

The Everhour MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Everhour account. It provides structured and secure access to your time tracking, client, and expense data, so your agent can perform actions like listing clients, retrieving expenses, managing projects, and fetching user profiles on your behalf.

  • Comprehensive client management: Ask your agent to list, create, or delete clients to keep your workspace organized and up-to-date.
  • Expense tracking and review: Effortlessly retrieve all expenses or list available expense categories to monitor spending and streamline expense management.
  • Project and section insights: Have your agent fetch detailed information about specific projects or sections using their IDs for better resource planning.
  • Personalized user profile access: Enable your agent to fetch the authenticated user's profile for quick access to account details and preferences.
  • Webhook configuration overview: List all configured webhooks to monitor integrations and automate notifications within your Everhour environment.

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

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Everhour account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
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 python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Everhour via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Everhour connections to use
5

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Everhour session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["everhour"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Everhour tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed
7

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Everhour assistant agent with MCP tools
    agent = AssistantAgent(
        name="everhour_assistant",
        description="An AI assistant that helps with Everhour operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Everhour tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Everhour related question or task to the agent.\n")

# Conversation loop
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")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Everhour tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Everhour and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

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

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Everhour assistant agent with MCP tools
        agent = AssistantAgent(
            name="everhour_assistant",
            description="An AI assistant that helps with Everhour operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Everhour related question or task to the agent.\n")

        # Conversation loop
        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")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

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

Conclusion

You now have an Autogen assistant wired into Everhour through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Everhour, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

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

Add Time

Add or upsert tracked time for a task, user, and date.

Create Client

Creates a new client in Everhour for tracking billable work, invoicing, and project organization.

Delete a client

Tool to delete a client.

List Clients

Retrieves all clients in the Everhour workspace.

Clock In User

Tool to clock in a user for time tracking.

Clock Out User

Tool to clock out a user for time tracking.

Create Webhook

Tool to create a new webhook for event notifications in Everhour.

Delete Webhook

Tool to delete a webhook.

Delete a timecard

Delete a user's timecard for a specific date in Everhour.

Delete Time Record

Remove tracked time by record ID while retaining its history trail.

Discard Timesheet Approval

Withdraw the authenticated user's previously submitted timesheet approval request for a week.

List Expenses

List expense records logged by the authenticated user in Everhour.

Get Client by ID

Tool to retrieve a specific client by ID.

Get Current Timer

Get the authenticated Everhour user's current timer state.

Get Project

Tool to retrieve a specific project.

Get Projects Report

Return aggregated Everhour project time and financial metrics.

Get Section

Retrieve details of a specific section by its ID.

Get Task

Retrieve one native or integration-backed Everhour task by ID.

Get Task Time Records

Lists tracked-time records for an Everhour task with date and page filters.

Get Timecard

Tool to retrieve a specific timecard for a user on a date.

Get Authenticated User Profile

Tool to retrieve profile information of the authenticated user.

Get User Time Records

List one Everhour user's tracked-time records.

Get Webhook

Retrieve details of a specific webhook by its ID.

List Expense Categories

Lists all expense categories available in your Everhour account.

List Webhooks

List webhooks created with the Everhour API key, including their target URLs, subscribed events, active status, and timestamps.

List Invoices

Retrieves all invoices from your Everhour workspace.

List projects

Lists Everhour projects accessible to the authenticated user, with optional name, status, platform, and result-limit parameters.

List Project Tasks

List tasks in an Everhour project with optional filters and pagination.

List Project Time Records

List tracked-time records for an Everhour project.

List Sections

Lists all sections within a specific Everhour project.

List Tags

List all tags in the Everhour workspace.

List Team Members

Retrieves team members in the authenticated Everhour workspace, including IDs, names, roles, and statuses.

List Teams

Retrieves information about the authenticated team/workspace in Everhour.

List Team Time Records

List team time records for a date range; without dates, return only today.

List Timecards

Retrieves team timecards, including clock-in/out data and work hours, with optional date filtering.

List User Timecards

Retrieves a specific user's timecards, including clock-in/out data and work hours, with optional date filtering.

List User Timesheets

Tool to retrieve timesheets for a specific user.

Create Project

Tool to create a new project in Everhour.

Delete a project

Permanently deletes an Everhour project by ID, including its tasks and associated time records.

Request Timesheet Approval

Tool to request approval for a timesheet or approve a week (for admins).

Search Tasks

Search accessible Everhour tasks, optionally including closed tasks.

Create Section

Tool to create a new section in a project.

Delete a section

Tool to delete a section.

Create Task

Creates a new task in an Everhour project.

Start Timer

Tool to start a new timer for a task.

Update Client

Tool to update an existing client in Everhour.

Update Expense

Partially update an existing Everhour expense.

Update an existing project

Updates an existing Everhour project's settings by project ID, including its name or notes.

Update Timecard

Update or create a user's timecard for a specific date, setting clock-in, clock-out, or break duration.

Update Time Record

Update an existing tracked-time record by its record ID.

Update Webhook

Update an existing Everhour webhook's subscribed events or project filter.

FRAMEWORKS

How to build Everhour MCP Agent with another framework

Claude Code logo

Claude Code

Use Everhour MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Everhour MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Everhour MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Everhour MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Everhour MCP with Grok Bot

Codex logo

Codex

Use Everhour MCP with Codex

OpenClaw logo

OpenClaw

Use Everhour MCP with OpenClaw

Hermes logo

Hermes

Use Everhour MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Everhour MCP with Atomic Agent

Google ADK logo

Google ADK

Use Everhour MCP with Google ADK

LangChain logo

LangChain

Use Everhour MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Everhour MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Everhour MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Everhour MCP with LlamaIndex

CrewAI logo

CrewAI

Use Everhour MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Everhour MCP with Pydantic AI

FAQ

Frequently asked questions

Start with Everhour.It takes 30 seconds.

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

Start building