How to integrate Habitica MCP with Vercel AI SDK v6

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

30 min · no commitment · see it on your stack

Habitica logo
Vercel AI SDK logo
divider

Introduction

This guide walks you through connecting Habitica to Vercel AI SDK v6 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working Habitica agent that can add a new daily task for exercise, create a challenge for team productivity, delete an outdated task from your challenge through natural language commands.

This guide will help you understand how to give your Vercel AI SDK 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.

Also integrate Habitica with

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Habitica integration
  • Using Composio's Tool Router to dynamically load and access Habitica tools
  • Creating an MCP client connection using HTTP transport
  • Building an interactive CLI chat interface with conversation history management
  • Handling tool calls and results within the Vercel AI SDK framework

What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.

Key features include:

  • streamText: Core function for streaming responses with real-time tool support
  • MCP Client: Built-in support for Model Context Protocol via @ai-sdk/mcp
  • Step Counting: Control multi-step tool execution with stopWhen: stepCountIs()
  • OpenAI Provider: Native integration with OpenAI models

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.
Add Push DeviceTool to register a push notification device for the authenticated user.
Add Tag to TaskTool to add a tag to a task.
Clone ChallengeTool to clone an existing challenge.
Create ChallengeTool to create a new challenge.
Create Habitica PartyCreate a new Habitica party for collaborative gameplay.
Create TagTool to create a new tag.
Create TaskCreate a new task in Habitica.
Create WebhookTool to create a new webhook for taskActivity events.
Delete Habitica ChallengePermanently delete a Habitica challenge.
Leave or Delete Habitica GroupLeave or delete a Habitica group (party or guild).
Delete Group Chat MessageTool to delete a chat message from a Habitica group (party, guild, or Tavern).
Delete Habitica TagTool to delete a tag for the authenticated user.
Delete TaskPermanently deletes a user's task (habit, daily, todo, or reward) by its ID.
Delete Task Checklist ItemTool to delete a checklist item from a task.
Delete User MessageTool to delete a message from the authenticated user's inbox by its ID.
Delete User Push DeviceTool to remove a push device registration from the authenticated user's account.
Equip ItemTool to equip or unequip gear, pets, mounts, or costume items in Habitica.
Export Challenge to CSVTool to export a Habitica challenge to CSV format.
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 Task by IDRetrieve a task by its unique ID.
Get Challenge TasksTool to get all tasks for a specified challenge.
Get ContentRetrieves all Habitica game content definitions in a single request.
Get Content By TypeRetrieves Habitica game content data filtered by a specific category type.
Get Export History CSVTool to export user tasks history in CSV format.
Get Export Inbox HTMLTool to export inbox data in HTML format from Habitica.
Export User Data JSONExports the authenticated user's complete data in JSON format.
Get GroupRetrieves detailed information about a Habitica group (guild or party).
Get Group MembersRetrieve members of a Habitica group (guild or party).
Get Habitica GroupsRetrieves Habitica groups based on type.
Get Habitica Tavern GroupTool to retrieve the Habitica Tavern (habitrpg) group details.
Get Party Chat MessagesTool to retrieve party chat messages from Habitica.
Get Model PathsRetrieves all available field paths and their data types for a specified Habitica model.
Get NewsTool to retrieve the latest Bailey announcement from Habitica.
Get PartyRetrieves the authenticated user's party details from Habitica.
Get Shops Market GearTool to retrieve the available gear for purchase in the market shop.
Get Time Travelers ShopTool to retrieve available items in the Time Travelers shop.
Get Habitica API StatusTool to check Habitica API server status.
Get TagsRetrieve all tags for the authenticated Habitica user.
Get TasksTool to retrieve all tasks for the authenticated user.
Get User ChallengesTool to retrieve challenges the authenticated user participates in.
Get User ProfileRetrieves the authenticated user's complete Habitica profile.
Get WebhooksRetrieves all webhooks configured for the authenticated Habitica user.
Get World StateRetrieves the current state of the Habitica game world including active events, world boss status, and seasonal NPC visual themes.
Invite To GroupTool to invite users to a specific group.
Invite To QuestTool to invite party members to a quest.
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 Group Chat SeenTool to mark all chat messages as read/seen for a specific group.
Mark Notification SeenTool to mark a single notification as seen in Habitica.
Mark Notifications SeenMarks specific notifications as read/seen in Habitica.
Move Pinned ItemTool to move a pinned item in the rewards column to a new position.
Move Task To PositionMove a Habitica task to a new position in the task list.
Dismiss Bailey AnnouncementTool to dismiss the latest Bailey announcement in Habitica, allowing it to be read later.
Reset User AccountResets the authenticated user's account to starting state.
Read CardTool to mark a card as read in Habitica.
Remove Party MemberRemoves a member from the authenticated user's party.
Score TaskScore a Habitica task to mark it as completed or incomplete.
Social AuthTool to authenticate a user via a social provider.
Subscribe WebhookTool to enable (subscribe) an existing webhook by ID for the authenticated user.
Unlink All Challenge TasksTool to unlink all tasks from a Habitica challenge.
Update GroupTool to update a Habitica group (party or guild) by modifying its properties.
Update TagTool to update an existing tag's name.
Update TaskUpdate an existing task in Habitica.
Update Task Checklist ItemTool to update a checklist item in a task.
Update UserUpdate the authenticated user's profile, preferences, flags, and other settings in Habitica.
Validate Coupon CodeValidate a Habitica coupon code to check if it is valid and active.

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:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key

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 required dependencies

bash
npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv

First, install the necessary packages for your project.

What you're installing:

  • @ai-sdk/openai: Vercel AI SDK's OpenAI provider
  • @ai-sdk/mcp: MCP client for Vercel AI SDK
  • @composio/core: Composio SDK for tool integration
  • ai: Core Vercel AI SDK
  • dotenv: Environment variable management

Set up environment variables

bash
OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

Create a .env file in your project root.

What's needed:

  • OPENAI_API_KEY: Your OpenAI API key for GPT model access
  • COMPOSIO_API_KEY: Your Composio API key for tool access
  • COMPOSIO_USER_ID: A unique identifier for the user session

Import required modules and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});
What's happening:
  • We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
  • The dotenv/config import automatically loads environment variables
  • The MCP client import enables connection to Composio's tool server

Create Tool Router session and initialize MCP client

typescript
async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["habitica"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Habitica tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned mcp object contains the URL and authentication headers needed to connect to the MCP server
  • This session provides access to all Habitica-related tools through the MCP protocol

Connect to MCP server and retrieve tools

typescript
const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();
What's happening:
  • We're creating an MCP client that connects to our Composio Tool Router session via HTTP
  • The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
  • The type: "http" is important - Composio requires HTTP transport
  • tools() retrieves all available Habitica tools that the agent can use

Initialize conversation and CLI interface

typescript
let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to habitica, like summarize my last 5 emails, send an email, etc... :)))\n",
);

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();
What's happening:
  • We initialize an empty messages array to maintain conversation history
  • A readline interface is created to accept user input from the command line
  • Instructions are displayed to guide the user on how to interact with the agent

Handle user input and stream responses with real-time tool feedback

typescript
rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • We use streamText instead of generateText to stream responses in real-time
  • toolChoice: "auto" allows the model to decide when to use Habitica tools
  • stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
  • onStepFinish callback displays which tools are being used in real-time
  • We iterate through the text stream to create a typewriter effect as the agent responds
  • The complete response is added to conversation history to maintain context
  • Errors are caught and displayed with helpful retry suggestions

Complete Code

Here's the complete code to get you started with Habitica and Vercel AI SDK:

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["habitica"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to habitica, like summarize my last 5 emails, send an email, etc... :)))\n",
  );

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
      console.log("\nGoodbye!");
      rl.close();
      process.exit(0);
    }

    if (!trimmedInput) {
      rl.prompt();
      return;
    }

    messages.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

Conclusion

You've successfully built a Habitica agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.

Key features of this implementation:

  • Real-time streaming responses for a better user experience with typewriter effect
  • Live tool execution feedback showing which tools are being used as the agent works
  • Dynamic tool loading through Composio's Tool Router with secure authentication
  • Multi-step tool execution with configurable step limits (up to 10 steps)
  • Comprehensive error handling for robust agent execution
  • Conversation history maintenance for context-aware responses

You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.

How to build Habitica MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Habitica MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Habitica MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Habitica MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Habitica MCP with Claude Cowork

Codex logo

Codex

Use Habitica MCP with Codex

OpenClaw logo

OpenClaw

Use Habitica MCP with OpenClaw

Hermes logo

Hermes

Use Habitica MCP with Hermes

CLI logo

CLI

Use Habitica MCP with CLI

Google ADK logo

Google ADK

Use Habitica MCP with Google ADK

LangChain logo

LangChain

Use Habitica MCP with LangChain

Mastra AI logo

Mastra AI

Use Habitica MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Habitica MCP with LlamaIndex

CrewAI logo

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 Vercel AI SDK v6?

Yes, you can. Vercel AI SDK v6 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
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↗