How to Use the Todoist MCP in Pydantic AI

Q: How do I check project structure with Todoist using Pydantic AI?

The system allows listing all projects via listprojects. For a deeper look into the organization, call listprojectsections to map out every section within that container.

Q: What is the process for updating tasks in Todoist using Pydantic AI?

The agent calls updatetaskdetails. Because of Pydantic's validation layer, you know with certainty that the data being passed (like a new description or date) matches the expected format.

Ensure correctness with Pydantic AI and Todoist task management.

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 Pydantic AI

Create your Vinkius account to connect Todoist to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create and manage all your To-Do items.

Start by calling `create_task` to add a brand new item to your list. If that task needs modification later, the agent uses `update_task_details`. This guarantees you're changing only what was intended. Need to close something out? Use `complete_task` to mark tasks as finished and keep records accurate.

Get a full view of Todoist projects.

The agent starts by running `list_projects` to get a list of all available project containers. This gives your system the necessary boundaries for work. The tool also provides `get_project_details`, pulling specific metadata on any given project so you know exactly what it contains.

Retrieve and filter task lists.

Use `list_active_tasks` to pull targeted results. You can specify filters by label, a particular project, or use the general filter option. It’s precise work. If you need all the details on one item, call `get_task_details`. This gives your agent everything it needs for validation against Pydantic models.

Setup guide

Set up Todoist MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "todoist-extended-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Todoist tools.",
)

result = await agent.run("List recent Todoist transactions")
print(result.output)

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 Pydantic AI

Pydantic validates every single response from the MCP Server. If the API returns unexpected fields—say, a missing due date—the agent fails loudly with an error, so you never have silent corruption.

The system allows listing all projects via `list_projects`. For a deeper look into the organization, call `list_project_sections` to map out every section within that container.

The agent calls `update_task_details`. Because of Pydantic's validation layer, you know with certainty that the data being passed (like a new description or date) matches the expected format.

The server handles task descriptions, labels, project names, and task status. All outputs are rigorously validated against defined Pydantic models, ensuring type safety.

Yes. If a task was accidentally completed but needs to be active again, the `reopen_task` tool handles that change and updates the status for you.

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