Where do I get my Todoist API Token?

You can locate your personal API Token securely via the web application by clicking your profile avatar, going to **Settings**, and selecting the **Integrations** tab. Your token will be visible at the bottom or in a dedicated Developer section. Alternatively, navigate directly to `https://todoist.com/prefs/integrations`.

Can the agent delete projects or workspaces?

No. The integration exclusively lists resources (projects, items, labels) and supports only basic item modifications: creating tasks and marking tasks as completed. Destructive actions on structural settings are not supported.

Can the agent organize my tasks using sub-projects or sections?

Yes. The Todoist integration allows the agent to retrieve project IDs and navigate into their specific sections. When creating a new task, you can explicitly ask the agent to place it within a specific section to keep your work neatly organized.

Todoist MCP Server for Pydantic AI 7 tools — connect in under 2 minutes

Name: Todoist
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 7 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Todoist through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Todoist "
            "(7 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Todoist?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Todoist MCP Server

Connect your Todoist account to any AI agent and bring your daily productivity directly into your chat. View your active tasks, manage projects, and quickly add new items to your workflow entirely through conversational commands without ever needing to open the app.

Pydantic AI validates every Todoist tool response against typed schemas, catching data inconsistencies at build time. Connect 7 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Project Management — List all your active project folders, retrieve their specific IDs, and view sections within specific projects
Task Execution — View your complete list of pending tasks and mark them as completed instantly
Create Tasks — Add new items to a specific project or your inbox naturally in plain conversation
Organization — Look up available labels/tags to categorize your work
Collaboration — Read through existing comments to catch up on discussion history for any particular task

The Todoist MCP Server exposes 7 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Todoist to Pydantic AI via MCP

Follow these steps to integrate the Todoist MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 7 tools from Todoist with type-safe schemas

Why Use Pydantic AI with the Todoist MCP Server

Pydantic AI provides unique advantages when paired with Todoist through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Todoist integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Todoist connection logic from agent behavior for testable, maintainable code

Todoist + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Todoist MCP Server delivers measurable value.

Type-safe data pipelines: query Todoist with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Todoist tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Todoist and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Todoist responses and write comprehensive agent tests

Todoist MCP Tools for Pydantic AI (7)

These 7 tools become available when you connect Todoist to Pydantic AI via MCP:

complete_task

Marks a task as completed

create_task

Provide content and an optional project ID. Creates a new task in Todoist

list_comments

Lists all comments for a specific task

list_labels

Lists all user-defined labels

list_projects

Lists all active projects in Todoist

list_sections

Lists all sections within a specific project

list_tasks

Can filter by project_id. Lists active tasks, optionally filtered by project

Example Prompts for Todoist in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Todoist immediately.

"Check all my active tasks and projects."

"Complete the task with ID 81229."

Troubleshooting Todoist MCP Server with Pydantic AI

Common issues when connecting Todoist to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Todoist + Pydantic AI FAQ

Common questions about integrating Todoist MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Todoist MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.