How to integrate Everhour MCP with LlamaIndex

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Everhour logo
LlamaIndex logo
divider

Introduction

This guide walks you through connecting Everhour to LlamaIndex using the Composio tool router. By the end, you'll have a working Everhour agent that can list all clients for this workspace, retrieve expense categories for new report, get your everhour user profile details through natural language commands.

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

Also integrate Everhour with

TL;DR

Here's what you'll learn:
  • Set your OpenAI and Composio API keys
  • Install LlamaIndex and Composio packages
  • Create a Composio Tool Router session for Everhour
  • Connect LlamaIndex to the Everhour MCP server
  • Build a Everhour-powered agent using LlamaIndex
  • Interact with Everhour through natural language

What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.

Key features include:

  • ReAct Agent: Reasoning and acting pattern for tool-using agents
  • MCP Tools: Native support for Model Context Protocol
  • Context Management: Maintain conversation context across interactions
  • Async Support: Built for async/await patterns

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.

Supported Tools & Triggers

Tools
Create ClientCreates a new client in Everhour for tracking billable work, invoicing, and project organization.
Delete a clientTool to delete a client.
List ClientsRetrieves all clients in the Everhour workspace.
Clock In UserTool to clock in a user for time tracking.
Clock Out UserTool to clock out a user for time tracking.
Create WebhookTool to create a new webhook for event notifications in Everhour.
Delete WebhookTool to delete a webhook.
Delete a timecardTool to delete a timecard for a user on a specific date.
Discard Timesheet ApprovalTool to discard a pending timesheet approval request.
List ExpensesLists expense records from your Everhour workspace.
Get Client by IDTool to retrieve a specific client by ID.
Get ProjectTool to retrieve a specific project.
Get SectionRetrieve details of a specific section by its ID.
Get TimecardTool to retrieve a specific timecard for a user on a date.
Get Authenticated User ProfileTool to retrieve profile information of the authenticated user.
Get WebhookRetrieve details of a specific webhook by its ID.
List Expense CategoriesLists all expense categories available in your Everhour account.
List WebhooksLists all webhooks configured for the Everhour account.
List InvoicesRetrieves all invoices from your Everhour workspace.
List projectsList all Everhour projects accessible by the authenticated user.
List SectionsLists all sections within a specific Everhour project.
List TagsList all tags in the Everhour workspace.
List Team MembersRetrieves all team members in the authenticated Everhour workspace.
List TeamsRetrieves information about the authenticated team/workspace in Everhour.
List TimecardsTool to retrieve all team timecards with optional date filtering.
List User TimecardsTool to retrieve timecards for a specific user with optional date filtering.
List User TimesheetsTool to retrieve timesheets for a specific user.
Create ProjectTool to create a new project in Everhour.
Delete a projectTool to delete a project.
Request Timesheet ApprovalTool to request approval for a timesheet or approve a week (for admins).
Create SectionTool to create a new section in a project.
Delete a sectionTool to delete a section.
Create TaskCreates a new task in an Everhour project.
Start TimerTool to start a new timer for a task.
Update ClientTool to update an existing client in Everhour.
Update an existing projectUpdates an existing Everhour project's settings.
Update TimecardTool to update a timecard for a user on a specific date.
Update WebhookTool to update an existing webhook configuration in Everhour.

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

Prerequisites

Before you begin, make sure you have:
  • Python 3.8/Node 16 or higher installed
  • A Composio account with the API key
  • An OpenAI API key
  • A Everhour account and project
  • Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Everhour

OpenAI API key (OPENAI_API_KEY)
  • Go to the OpenAI dashboard
  • Create an API key if you don't have one
  • Assign it to OPENAI_API_KEY in .env
Composio API key and user ID
  • Log into the Composio dashboard
  • Copy your API key from Settings
    • Use this as COMPOSIO_API_KEY
  • Pick a stable user identifier (email or ID)
    • Use this as COMPOSIO_USER_ID

Installing dependencies

pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv

Create a new Python project and install the necessary dependencies:

  • composio-llamaindex: Composio's LlamaIndex integration
  • llama-index: Core LlamaIndex framework
  • llama-index-llms-openai: OpenAI LLM integration
  • llama-index-tools-mcp: MCP client for LlamaIndex
  • python-dotenv: Environment variable management

Set environment variables

bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id

Create a .env file in your project root:

These credentials will be used to:

  • Authenticate with OpenAI's GPT-5 model
  • Connect to Composio's Tool Router
  • Identify your Composio user session for Everhour access

Import modules

import asyncio
import os
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

Create a new file called everhour_llamaindex_agent.py and import the required modules:

Key imports:

  • asyncio: For async/await support
  • Composio: Main client for Composio services
  • LlamaIndexProvider: Adapts Composio tools for LlamaIndex
  • ReActAgent: LlamaIndex's reasoning and action agent
  • BasicMCPClient: Connects to MCP endpoints
  • McpToolSpec: Converts MCP tools to LlamaIndex format

Load environment variables and initialize Composio

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

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_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")

What's happening:

This ensures missing credentials cause early, clear errors before the agent attempts to initialise.

Create a Tool Router session and build the agent function

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["everhour"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")

    description = "An agent that uses Composio Tool Router MCP tools to perform Everhour actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Everhour actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)

What's happening here:

  • We create a Composio client using your API key and configure it with the LlamaIndex provider
  • We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, everhour)
  • The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
  • LlamaIndex will connect to this endpoint to dynamically discover and use the available Everhour tools.
  • The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.

Create an interactive chat loop

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

What's happening here:

  • We're creating a direct terminal interface to chat with your Everhour database
  • The LLM's responses are streamed to the CLI for faster interaction.
  • The agent uses context to maintain conversation history
  • You can type 'quit' or 'exit' to stop the chat loop gracefully
  • Agent responses and any errors are displayed in a clear, readable format

Define the main entry point

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

What's happening here:

  • We're orchestrating the entire application flow
  • The agent gets built with proper error handling
  • Then we kick off the interactive chat loop so you can start talking to Everhour

Run the agent

npx ts-node llamaindex-agent.ts

When prompted, authenticate and authorise your agent with Everhour, then start asking questions.

Complete Code

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

import asyncio
import os
import signal
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

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

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set")
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")

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["everhour"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")
    description = "An agent that uses Composio Tool Router MCP tools to perform Everhour actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Everhour actions.
    """
    return ReActAgent(
        tools=tools,
        llm=llm,
        description=description,
        system_prompt=system_prompt,
        verbose=True,
    );

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

Conclusion

You've successfully connected Everhour to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:
  • Tool Router dynamically exposes Everhour tools through an MCP endpoint
  • LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
  • The agent becomes more capable without increasing prompt size
  • Async Python provides clean, efficient execution of agent workflows
You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.

How to build Everhour MCP Agent with another framework

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

Claude Code logo

Claude Code

Use Everhour MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Everhour MCP with Claude Cowork

Codex logo

Codex

Use Everhour MCP with Codex

OpenClaw logo

OpenClaw

Use Everhour MCP with OpenClaw

Hermes logo

Hermes

Use Everhour MCP with Hermes

CLI logo

CLI

Use Everhour MCP with CLI

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

CrewAI logo

CrewAI

Use Everhour MCP with CrewAI

FAQ

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

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

Can I use Tool Router MCP with LlamaIndex?

Yes, you can. LlamaIndex 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 Everhour tools.

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

Yes, absolutely. You can configure which Everhour 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 Everhour data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
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.

Get started for freeGet a demo↗