SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Ticktick MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Ticktick MCP. Add a new task for tomorrow morning, complete all overdue tasks in your inbox, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Ticktick logoTicktick
Oauth2

TickTick is a cross-platform task management and to-do list app. It helps you organize tasks, set reminders, and stay on top of your schedule.

22 Tools

Introduction

This guide walks you through connecting Ticktick to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Ticktick agent that can create and update tasks, complete and move tasks, manage projects, add task comments, and filter tasks through natural language commands.

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

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

Also integrate Ticktick with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKLangChainMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

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

The Ticktick MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Ticktick account. It provides structured and secure access to your task lists and projects, so your agent can create, manage, and organize tasks, complete or delete items, and streamline your productivity workflows automatically.

  • Automated task creation and editing: Let your agent add new tasks, set deadlines, and update task details across your Ticktick projects with ease.
  • Project management and organization: Direct your agent to create, retrieve, or delete entire projects, keeping your workspace tidy and aligned with your priorities.
  • Seamless task completion and cleanup: Ask your agent to mark tasks as complete or delete tasks you've finished or no longer need, helping you stay on top of your to-do list.
  • Comprehensive project data retrieval: Have your agent fetch detailed project information, including all associated tasks and columns, for quick overviews or reporting.
  • Effortless OAuth2 authentication management: Benefit from a streamlined, agent-guided authorization flow that securely connects your Ticktick account with minimal friction.

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

Step by step09 STEPS
1

Prerequisites

Before you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key
2

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.
3

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
4

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
5

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
6

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: ["ticktick"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Ticktick 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 Ticktick-related tools through the MCP protocol
7

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 Ticktick tools that the agent can use
8

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 ticktick, 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
9

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 Ticktick 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 Ticktick 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: ["ticktick"],
  });

  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 ticktick, 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 Ticktick 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.
TOOLS

Supported Tools

Every Ticktick action and event your agent gets out of the box.

Add Task Comment

Add a discussion comment to a task in a TickTick project.

Batch Create Or Update Tasks

Create and update up to 50 TickTick tasks per operation in one request.

Complete Task

Mark a TickTick task as complete using its project ID and task ID.

Create Column

Create a named column in an existing TickTick project.

Create Project

Create a new project (list) in TickTick.

Create Task

Tool to create a new task in TickTick.

Delete TickTick Project

Permanently deletes a TickTick project by its ID.

Delete Task

Tool to permanently delete a specific task — irreversible, no recovery.

Filter Tasks

Return up to 200 tasks matching project, start-date, priority, tag, kind, and status filters.

Get Project By ID

Tool to retrieve a specific TickTick project by its unique ID.

Get project with data

Retrieve a TickTick project's metadata, undone tasks, and columns by project ID.

Get Task By Project And ID

Tool to retrieve a specific TickTick task by project ID and task ID.

Get User Projects

Retrieves projects accessible to the authenticated user, including their IDs and metadata such as name, color, view mode, and organization details.

List All Tasks

List open tasks across TickTick projects, with project context.

List Completed Tasks

Return up to 200 completed tasks, optionally filtered by project and completion date.

List Project Members

List the users who belong to a TickTick project.

List Tags

List the tags available to the connected TickTick account.

List Task Comments

List discussion comments attached to a task in a TickTick project.

Move Tasks

Move one or more existing tasks between TickTick projects.

Generate OAuth2 Authorization URL

Tool to generate the TickTick OAuth2 authorization URL.

Update Project

Tool to update an existing project.

Update Task

Updates an existing TickTick task identified by task ID and project ID, with optional task details such as dates, reminders, recurrence, priority, and checklist items.

FRAMEWORKS

How to build Ticktick MCP Agent with another framework

Claude Code logo

Claude Code

Use Ticktick MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Ticktick MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Ticktick MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Ticktick MCP with Claude Agent SDK

Codex logo

Codex

Use Ticktick MCP with Codex

OpenClaw logo

OpenClaw

Use Ticktick MCP with OpenClaw

Hermes logo

Hermes

Use Ticktick MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Ticktick MCP with Atomic Agent

Google ADK logo

Google ADK

Use Ticktick MCP with Google ADK

LangChain logo

LangChain

Use Ticktick MCP with LangChain

Mastra AI logo

Mastra AI

Use Ticktick MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Ticktick MCP with LlamaIndex

CrewAI logo

CrewAI

Use Ticktick MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Ticktick MCP with Pydantic AI

AutoGen logo

AutoGen

Use Ticktick MCP with AutoGen

FAQ

Frequently asked questions

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

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 Ticktick tools.

Yes, absolutely. You can configure which Ticktick 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.

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 Ticktick data and credentials are handled as safely as possible.

Start with Ticktick.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Ticktick tool your agent needs.Free to start.

Start building