How to Use the Todoist MCP in Google ADK

Q: What if I need to check project structure with Todoist using Google ADK?

The agent uses listprojectsections to map out all the sections within a given project. This ensures your system understands the full organizational depth of the workspace.

Q: Can I search and filter tasks with Todoist using Google ADK?

Yes, listactivetasks lets you specify filters by label or project name. You just tell your agent what parameters to use, and it returns a highly relevant subset of data.

Q: What data types does this MCP Server touch for Todoist with Google ADK?

It manages task descriptions, labels, due dates (via updatetaskdetails), project names, and the completion status. It touches all core task attributes.

Q: How do I handle old or closed tasks in Todoist using Google ADK?

If a task was finished but needs to be revisited, use reopentask. This marks the item as active again, making it visible for current planning cycles.

Manage your entire workflow with Google ADK and Todoist.

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 Google ADK

Create your Vinkius account to connect Todoist to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

View all projects available in the MCP Server.

The `list_projects` tool quickly pulls a list of every project you manage inside Todoist. This is the first step your agent takes to get visibility across your entire workload. The metadata for any single project lives with `get_project_details`. Your agent can use this to understand the scope and contents before attempting to modify anything.

Create, update, or mark tasks as finished.

Need a new item? The `create_task` tool lets your agent drop off brand-new to-dos. Conversely, if you need to fix an existing task, the `update_task_details` function modifies it on the fly. When the job's done, call `complete_task`. This moves the item from 'to do' to 'finished,' keeping your list clean.

List and filter active Todoist tasks.

Your agent uses `list_active_tasks` to pull a targeted list, letting you specify filters by project or label. It avoids overwhelming you with data that isn't relevant right now. If the agent needs granular information, it can call `get_task_details`. This provides every piece of context for one specific task.

Setup guide

Set up Todoist MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Todoist tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Todoist_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Todoist tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

The agent accesses the MCP Server tools, allowing it to read and write data. For instance, you can use `create_task` or `update_task_details` without needing to switch apps.

The agent uses `list_project_sections` to map out all the sections within a given project. This ensures your system understands the full organizational depth of the workspace.

Yes, `list_active_tasks` lets you specify filters by label or project name. You just tell your agent what parameters to use, and it returns a highly relevant subset of data.

It manages task descriptions, labels, due dates (via `update_task_details`), project names, and the completion status. It touches all core task attributes.

If a task was finished but needs to be revisited, use `reopen_task`. This marks the item as active again, making it visible for current planning cycles.

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