How to integrate Wakatime MCP with LlamaIndex

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

30 min · no commitment · see it on your stack

Wakatime logo
LlamaIndex logo
divider

Introduction

This guide walks you through connecting Wakatime to LlamaIndex using the Composio tool router. By the end, you'll have a working Wakatime agent that can show your top coding languages this week, summarize today's coding activity by project, list your most productive coding days last month through natural language commands.

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

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

Also integrate Wakatime 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 Wakatime
  • Connect LlamaIndex to the Wakatime MCP server
  • Build a Wakatime-powered agent using LlamaIndex
  • Interact with Wakatime 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 Wakatime MCP server, and what's possible with it?

The Wakatime MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Wakatime account. It provides structured and secure access to your coding activity and productivity data, so your agent can analyze time spent coding, summarize project progress, generate reports, and surface productivity trends on your behalf.

  • Code activity summaries and analytics: Your agent can pull detailed breakdowns of your coding hours by language, project, or editor to help you understand where your time goes.
  • Project progress tracking: Get automatic updates on how much time you've dedicated to individual projects, making it easy to monitor deadlines and progress.
  • Personal productivity insights: Let your agent surface trends, highlight most productive days or hours, and offer suggestions for improving your workflow based on historical data.
  • Automated weekly and monthly reports: Have the agent generate and deliver summary reports of your coding habits, helping you spot patterns and areas for improvement.
  • Goal tracking and notifications: Enable your agent to track coding goals and notify you when milestones are reached or if you're falling behind.

Supported Tools & Triggers

Tools
Get Aggregate StatsTool to retrieve aggregate coding statistics across all WakaTime users for a given time range.
Get current user's status bar summary for todayTool to get current user's coding activity today for displaying in IDE status bars.
List IDE PluginsTool to list WakaTime IDE plugins with metadata.
List GoalsTool to list a user's goals with progress series and metadata.
Get User InsightTool to retrieve an insight for a user over a time range.
List LeadersTool to list public leaders ranked by coding activity.
List Machine NamesTool to list a user's machines including last seen time.
Get API Meta InformationTool to retrieve WakaTime API meta information, including public IP addresses used by WakaTime servers.
Generate WakaTime OAuth authorize URLTool to generate OAuth 2.
Get User DetailsTool to get detailed profile information for a WakaTime user by user ID or username.
Get User's Total Time Since CreationTool to retrieve total coding time since account creation for a user.
Get User StatsTool to retrieve coding statistics for a user over the default time range.
Get User Stats by RangeTool to retrieve comprehensive coding statistics for a user over a specific time range.
Get User SummariesGet user's coding activity for a time range as daily summaries.
List Program LanguagesTool to list all verified program languages supported by WakaTime.
List User ProjectsList WakaTime projects for a specified user.
List User AgentsTool to list plugins and editors which have sent data for a specified user.

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 Wakatime account and project
  • Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Wakatime

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 Wakatime 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 wakatime_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=["wakatime"],
    )

    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 Wakatime actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Wakatime 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, wakatime)
  • 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 Wakatime 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 Wakatime 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 Wakatime

Run the agent

npx ts-node llamaindex-agent.ts

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

Complete Code

Here's the complete code to get you started with Wakatime 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=["wakatime"],
    )

    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 Wakatime actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Wakatime 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 Wakatime to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:
  • Tool Router dynamically exposes Wakatime 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 Wakatime MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Wakatime MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Wakatime MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Wakatime MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Wakatime MCP with Claude Cowork

Codex logo

Codex

Use Wakatime MCP with Codex

OpenClaw logo

OpenClaw

Use Wakatime MCP with OpenClaw

Hermes logo

Hermes

Use Wakatime MCP with Hermes

CLI logo

CLI

Use Wakatime MCP with CLI

Google ADK logo

Google ADK

Use Wakatime MCP with Google ADK

LangChain logo

LangChain

Use Wakatime MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Wakatime MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Wakatime MCP with Mastra AI

CrewAI logo

CrewAI

Use Wakatime MCP with CrewAI

FAQ

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

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

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

Yes, absolutely. You can configure which Wakatime 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 Wakatime 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↗