How to Use the Todoist MCP in AutoGen

Q: How does Todoist work with AutoGen for project planning?

The agents start by gathering data using listprojects and getprojectdetails. They debate the best structure, leading to a final decision on whether to call createproject or modify an existing one.

Q: If I use Todoist with AutoGen, how are updates managed?

The agents decide why an update is needed (e.g., changing details or adding labels) after discussing the current state using gettaskdetails. They then execute the change via updatetaskdetails.

Q: Does Todoist support fetching task lists for AutoGen?

Yes. The listactivetasks tool lets the agents gather a filtered list (by label, project) which they can then use as evidence in their multi-agent conversations.

Force agents to debate decisions using Todoist data. The perfect fit for AutoGen's conversation framework.

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 AutoGen

Create your Vinkius account to connect Todoist to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Negotiate task status changes

When multiple perspectives are needed, let your agents discuss the next steps. An agent can check current tasks using `list_active_tasks` while another evaluates if a project needs to be created via `create_project`. They debate which action is most necessary. The consensus-driven nature of AutoGen means that before calling tools like `complete_task` or `reopen_task`, the agents must argue and agree on the state change, providing a verifiable decision trail.

Structured project planning debates

Your multi-agent system can use `list_projects` to gather all potential scopes. One agent might suggest creating a new initiative using `create_project`, while another reviews existing projects via `get_project_details`. The outcome is a reasoned decision on the optimal scope. This deliberation process makes AutoGen ideal for planning, where simply listing projects isn't enough; you need consensus on which ones to focus on.

Review and modify task requirements

Need a complex decision about an existing item? One agent can retrieve the current details using `get_task_details`, while another reviews related comments via `list_comments`. They debate whether the task needs more information or if its description requires revision. The final step, modifying the task with `update_task_details`, isn't just an execution; it's the result of a negotiated agreement between your autonomous agents.

Setup guide

Set up Todoist MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Todoist tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Todoist_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Todoist data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Todoist_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Todoist data")
    print(result.messages[-1].content)

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 AutoGen

The agents start by gathering data using `list_projects` and `get_project_details`. They debate the best structure, leading to a final decision on whether to call `create_project` or modify an existing one.

Absolutely. If multiple agents disagree on a task's status, they debate it. The final decision—like calling `complete_task` or `reopen_task`—is based on the system's negotiated consensus.

The agents decide *why* an update is needed (e.g., changing details or adding labels) after discussing the current state using `get_task_details`. They then execute the change via `update_task_details`.

It exposes structured data like task titles, project sections (`list_project_sections`), labels, and comments. This rich input allows agents to debate using concrete evidence instead of general assumptions.

Yes. The `list_active_tasks` tool lets the agents gather a filtered list (by label, project) which they can then use as evidence in their multi-agent conversations.

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