How to integrate Habitica MCP with LlamaIndex

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Habitica Logo
LlamaIndex Logo
divider

Introduction

This guide walks you through connecting Habitica to LlamaIndex using the Composio tool router. By the end, you'll have a working Habitica agent that can add a new daily task for exercise, create a challenge for team productivity, delete an outdated task from my challenge, create a tag for urgent work tasks through natural language commands.

This guide will help you understand how to give your LlamaIndex agent real control over a Habitica account through Composio's Habitica 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:
  • Set your OpenAI and Composio API keys
  • Install LlamaIndex and Composio packages
  • Create a Composio Tool Router session for Habitica
  • Connect LlamaIndex to the Habitica MCP server
  • Build a Habitica-powered agent using LlamaIndex
  • Interact with Habitica 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 Habitica MCP server, and what's possible with it?

The Habitica MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Habitica account. It provides structured and secure access to your tasks, challenges, and groups, so your agent can create tasks, manage challenges, organize groups, and automate productivity routines on your behalf.

  • Automated task creation and management: Let your agent create new tasks, set up habits, or add to-dos to keep your productivity on track—no manual entry needed.
  • Challenge and group organization: Easily create, edit, or delete Habitica challenges and groups so you can coordinate goals and activities with teams or friends.
  • Tag and webhook automation: Have your agent generate new tags for smarter task sorting or set up webhooks for real-time notifications when tasks change or are completed.
  • Subscription and group membership management: Direct your agent to check or cancel subscriptions, leave parties, or delete groups as your needs change.
  • Seamless challenge task updates: Effortlessly add or remove tasks within challenges, helping you keep group goals relevant and up to date.

Supported Tools & Triggers

Tools
Add Task to ChallengeTool to add a new task to a specified challenge.
Cancel SubscriptionAttempts to cancel the authenticated user's subscription.
Create ChallengeTool to create a new challenge.
Create Habitica GroupTool to create a Habitica party or guild.
Create TagTool to create a new tag.
Create TaskTool to create a new user task in Habitica.
Create WebhookTool to create a new webhook for taskActivity events.
Delete a Habitica ChallengeTool to delete a challenge.
Delete Challenge TaskTool to delete a specific task from a challenge.
Delete Habitica GroupTool to delete a Habitica group (guild) or leave a party.
Delete Habitica TagTool to delete a tag for the authenticated user.
Delete TaskTool to delete a Habitica task.
Get Habitica AchievementsTool to retrieve all available Habitica achievements.
Get ChallengeTool to retrieve details of a specific challenge.
Get Group ChallengesTool to retrieve challenges available in a specific group (guild, party, or tavern).
Get Challenge TaskTool to retrieve a specific task from any challenge.
Get Challenge TasksTool to get all tasks for a specified challenge.
Get ContentTool to retrieve global game content definitions.
Get Content By TypeTool to retrieve game content for a specified category.
Get EquipmentTool to retrieve the authenticated user’s equipped gear and costume.
Get GroupTool to retrieve details of a specific group.
Get Group MembersTool to retrieve members of a specific group.
Get Habitica GroupsTool to retrieve Habitica groups (guilds, parties, taverns).
Get NotificationsTool to retrieve notifications for the authenticated user.
Get PartyTool to retrieve the authenticated user's party details.
Get Party MembersTool to retrieve members of the authenticated user's party.
Get TagsTool to retrieve authenticated user's tags.
Get TasksTool to retrieve all tasks for the authenticated user.
Get User AchievementsTool to retrieve the authenticated user's achievements.
Get User ChallengesTool to retrieve challenges the authenticated user participates in.
Get User InventoryTool to retrieve the authenticated user's full inventory.
Get User ProfileTool to retrieve the authenticated user's profile information.
Get User Quest ProgressTool to retrieve the authenticated user's quest progress.
Get User StatsTool to retrieve the authenticated user's Habitica statistics.
Get User SubscriptionTool to retrieve the authenticated user's subscription details.
Get WebhooksTool to retrieve webhooks for the authenticated user.
Invite To GroupTool to invite users to a specific group.
Invite To PartyTool to invite users to the authenticated user's party.
Join ChallengeTool to join a challenge.
Leave ChallengeTool to leave a Habitica challenge.
Local LoginTool to authenticate a user via local credentials.
Local User RegistrationTool to register a new Habitica user via email and password.
Mark Notifications SeenTool to mark specific notifications as read.
Remove Party MemberTool to remove a member from your party.
Score TaskTool to score (check/uncheck) a Habitica task.
Social AuthTool to authenticate a user via a social provider.
Subscribe WebhookTool to enable (subscribe) an existing webhook by ID for the authenticated user.

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

Getting API Keys for OpenAI, Composio, and Habitica

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 Habitica 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 habitica_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=["habitica"],
    )

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

Run the agent

npx ts-node llamaindex-agent.ts

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

Complete Code

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

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

OpenAI Agents SDK

OpenAI Agents SDK

Use Habitica MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Habitica MCP with Claude Agent SDK

Google ADK

Google ADK

Use Habitica MCP with Google ADK

LangChain

LangChain

Use Habitica MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Habitica MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Habitica MCP with Mastra AI

CrewAI

CrewAI

Use Habitica MCP with CrewAI

FAQ

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

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

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

Yes, absolutely. You can configure which Habitica 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 Habitica 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