How to Use the Todoist MCP in Vercel AI SDK

Q: How do I list Todoist tasks using Vercel AI SDK?

You call listtasks through your agent client. The results stream back to the UI, letting you display the active items instantly. This real-time data flow is key when building user-facing tools.

Q: Can I get project names for Todoist with Vercel AI SDK?

Yes, use listprojects to pull all the available projects into your application state. You can then map these IDs to human-readable names in your React component.

Q: Does Todoist support commenting via Vercel AI SDK?

Yep, you use listcomments and pass the specific task ID. This retrieves all associated comments for that item so your agent can display them immediately alongside the task details.

Q: How can I mark a Todoist task as complete using Vercel AI SDK?

You execute the completetask tool, passing in the specific task ID. The MCP Server handles updating the status in Todoist and confirms it back to your client.

Stream Todoist task data directly into your frontend UI using the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Todoist MCP to Vercel AI SDK

Create your Vinkius account to connect Todoist to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Todoist with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Check and List Tasks with Todoist

You can call `list_tasks` to grab a list of active items. You can also narrow that down by providing a specific `project_id`. This is perfect for showing users only the tasks relevant to the current screen. The MCP Server handles fetching the data and streaming it back instantly. When you use this, your agent client sees the results appear in real-time, avoiding any loading spinners.

Create New Todoist Tasks

Need to log a new item? Use `create_task`. You just pass the text content and optionally include a project ID. The agent handles making sure that task lands in the right spot. This function is fast and simple, letting you add tasks without needing an intermediate API call or complex state management on your end.

Manage Todoist Projects and Sections

The server lets you map out your workspace. Call `list_projects` to see what's active. From there, use `list_sections` if you need to drill down into the structure of a specific project. This structured data is essential for building robust frontends that accurately reflect how the user organizes their work.

Setup guide

Set up Todoist MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Todoist tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Todoist transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Todoist. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Todoist now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Todoist MCP in Vercel AI SDK

You call `list_tasks` through your agent client. The results stream back to the UI, letting you display the active items instantly. This real-time data flow is key when building user-facing tools.

Yes, use `list_projects` to pull all the available projects into your application state. You can then map these IDs to human-readable names in your React component.

Yep, you use `list_comments` and pass the specific task ID. This retrieves all associated comments for that item so your agent can display them immediately alongside the task details.

This server touches project IDs, task contents, section names, and comment text. It deals with structured textual data representing user tasks and organization metadata.

You execute the `complete_task` tool, passing in the specific task ID. The MCP Server handles updating the status in Todoist and confirms it back to your client.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript