How to integrate Todoist 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

Todoist logo
Vercel AI SDK logo
divider

Introduction

This guide walks you through connecting Todoist to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Todoist agent that can add a high-priority task for today, create a new project called 'team offsite', close all completed tasks from this week through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Todoist account through Composio's Todoist MCP server.

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

Also integrate Todoist with

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Todoist integration
  • Using Composio's Tool Router to dynamically load and access Todoist 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 Todoist MCP server, and what's possible with it?

The Todoist MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Todoist account. It provides structured and secure access to your tasks, projects, and labels, so your agent can create tasks, manage projects, add comments, organize sections, and update your to-do lists on your behalf.

  • Task creation and scheduling: Instantly ask your agent to add new tasks with specific details, deadlines, priorities, or even as subtasks within projects or sections.
  • Project and workspace management: Let your agent create, organize, or delete projects and workspaces to keep your productivity system tidy and up-to-date.
  • Section and label organization: Direct your agent to create, delete, or update sections and labels, helping you structure your tasks and filter lists for better focus.
  • Task completion and commenting: Have your agent mark tasks as complete or add helpful comments and notes to specific tasks or projects for seamless collaboration.
  • Streamlined cleanup and maintenance: Empower your agent to remove unused projects, labels, or sections, ensuring your Todoist stays clutter-free and organized.

Supported Tools & Triggers

Tools
Triggers
Add WorkspaceTool to create a new workspace in Todoist.
Archive Project (API v1)Tool to archive a project using Todoist API v1.
Bulk Create TasksCreate many tasks in one request using Todoist's Sync batching.
Close Task (API v1)Tool to close (complete) a task in Todoist using API v1.
Create Comment (API v1)Tool to create a new comment on a project or task using Todoist API v1.
Create Label (API v1)Tool to create a new personal label using API v1.
Create Project (API v1)Tool to create a new project in Todoist using the unified API v1.
Create Section (API v1)Tool to create a new section within a project using API v1.
Create taskCreate a new task in Todoist using the unified API v1.
Delete CommentTool to delete a specific comment from Todoist by its ID.
Delete Label (V1)Tool to delete a personal label using API v1.
Delete Project (API v1)Tool to delete a project and all of its sections and tasks using Todoist API v1.
Delete Section (v1)Tool to delete a section and all tasks within it.
Delete TaskTool to delete a specific task from Todoist.
Delete UploadTool to delete an uploaded file from Todoist.
Export Template As FileTool to export a Todoist project as a CSV template file.
Export Template As URLTool to export a Todoist project as a shareable template URL.
Filter TasksTool to get all tasks matching the filter.
Get All CommentsThis tool retrieves all comments associated with a specific task or project in Todoist.
Get all projectsGet all projects from a user's Todoist account.
Get All TasksFetches all INCOMPLETE tasks from Todoist and returns their details.
Get BackupsTool to list all available backup archives for the user.
Get Comment (V1)Tool to retrieve a single comment by ID using the v1 API.
Get Completed Tasks By Completion DateTool to retrieve completed tasks within a specified completion date window.
Get ID MappingsTool to translate IDs between Todoist API v1 and v2.
Get Personal LabelTool to retrieve a personal label by its ID.
Get Productivity StatsTool to retrieve comprehensive productivity statistics for the authenticated user.
Get Project (API v1)Tool to retrieve a specific project by its ID using Todoist API v1.
Get Full Project DataTool to retrieve full project data including all sections, tasks, and collaborators.
Get Project PermissionsTool to retrieve all available roles and their associated actions in Todoist projects.
Get Section (v1 API)Tool to retrieve a specific section by its ID using Todoist v1 API.
Get Special BackupsTool to list special backup archives for the authenticated user's projects.
Get Task (API v1)Tool to retrieve a single active (non-completed) task by ID using API v1.
Get UserTool to retrieve information about the currently authenticated user.
Get Workspace Plan DetailsTool to retrieve details about a workspace's current plan and usage.
Import Template Into Project By IDTool to import a template from Todoist's template gallery into an existing project.
Import Template Into Project From FileTool to import a CSV template into an existing Todoist project from a file.
Invite Project CollaboratorTool to invite a collaborator to a Todoist project by email.
List ActivitiesTool to get activity logs from Todoist.
List All Workspace InvitationsTool to return a list containing details of all pending invitations to a workspace.
List Archived ProjectsTool to get all archived projects from Todoist.
List Archived SectionsTool to retrieve all archived sections for a specific project in Todoist.
List Archived Workspace ProjectsTool to list all archived projects in a workspace.
List Completed TasksTool to retrieve all completed tasks with optional project filtering.
List Completed Tasks By Due DateTool to retrieve completed tasks within a specified due date range (up to 6 weeks).
List FiltersTool to list all filters for the authenticated user.
List Joinable WorkspacesTool to get workspaces the user can join.
List LabelsTool to get all user labels with pagination support.
List Pending Workspace InvitationsTool to list pending invitation emails in a workspace.
List Project CollaboratorsTool to get all collaborators for a given project with cursor-based pagination.
List SectionsTool to get all active sections for the user, with optional filtering by project.
List Shared LabelsTool to retrieve shared label names from active tasks with pagination support.
List Workspace Active ProjectsTool to list all active workspace projects.
List Workspace Archived ProjectsTool to get archived projects in a workspace.
List Workspace InvitationsTool to list user emails with pending invitations to a workspace.
List Workspace UsersTool to list users in workspace(s).
Move TaskTool to move a task to another project, section, or parent task while preserving task identity and metadata.
Move Task (REST API)Tool to move a task to another project, section, or parent task using the REST API.
Quick Add TaskTool to add tasks using natural language parsing similar to the official Todoist clients.
Remove Shared Label (API v1)Tool to remove a shared label from all active tasks using API v1.
Rename Shared Labels (API v1)Tool to rename a shared label across all active tasks using API v1.
Reopen Task (API v1)Tool to reopen a completed task in Todoist using API v1.
Reorder TasksReorder tasks deterministically by updating child_order in bulk via the Sync API item_reorder command.
Search LabelsTool to search user labels by name with case-insensitive matching.
Search ProjectsSearch active user projects by name with support for wildcards and pagination.
Search SectionsTool to search active sections by name, optionally filtered by project.
Todoist SyncTool to sync data with Todoist server, supporting both read and write operations.
Unarchive Project (API v1)Tool to unarchive a previously archived Todoist project using API v1.
Update Comment (v1)Tool to update a comment by ID and return its content via v1 API.
Update Label (API v1)Tool to update an existing label using API v1.
Update Notification SettingTool to update notification settings for the current user.
Update Project (API v1)Tool to update a project's properties using Todoist API v1.
Update Section (v1)Tool to update an existing section by its ID using Todoist v1 API.
Update TaskTool to update an existing task's properties.
Update Workspace LogoTool to upload an image as the workspace logo or delete the existing logo.
Upload FileTool to upload a file to Todoist.

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: ["todoist"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Todoist 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 Todoist-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 Todoist 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 todoist, 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 Todoist 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 Todoist 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: ["todoist"],
  });

  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 todoist, 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 Todoist 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 Todoist MCP Agent with another framework

ChatGPT logo

ChatGPT

Use Todoist MCP with ChatGPT

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Todoist MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Todoist MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Todoist MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Todoist MCP with Claude Cowork

Codex logo

Codex

Use Todoist MCP with Codex

Cursor logo

Cursor

Use Todoist MCP with Cursor

OpenClaw logo

OpenClaw

Use Todoist MCP with OpenClaw

Hermes logo

Hermes

Use Todoist MCP with Hermes

CLI logo

CLI

Use Todoist MCP with CLI

Google ADK logo

Google ADK

Use Todoist MCP with Google ADK

LangChain logo

LangChain

Use Todoist MCP with LangChain

Mastra AI logo

Mastra AI

Use Todoist MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Todoist MCP with LlamaIndex

CrewAI logo

CrewAI

Use Todoist MCP with CrewAI

OpenCode logo

OpenCode

Use Todoist MCP with OpenCode

VS Code logo

VS Code

Use Todoist MCP with VS Code

FAQ

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

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

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

Yes, absolutely. You can configure which Todoist 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 Todoist 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↗