How to Use the Todoist MCP in LangChain

Q: How do I search for tasks in Todoist using LangChain?

You start by calling listtasks. You can filter that list right away if you know the project ID, which saves time. The agent handles running those filters automatically.

Q: Can I create a new task in Todoist using LangChain?

Yep. Just tell your AI client to use createtask. You provide the content and optionally point it toward a project ID so it lands exactly where you want it.

Q: How does Todoist integrate with LangChain for data analysis?

The MCP Server exposes multiple tools, like listcomments or listlabels. Your agent calls these sequential steps to gather all necessary task metadata before you even start analyzing it.

Q: Does Todoist support project listing in LangChain?

Absolutely. The listprojects tool pulls every active project ID, giving your chain the full scope of what's available to work with.

Q: What kind of data does this MCP Server touch regarding Todoist privacy?

This server touches task metadata, including the projectid and general task content. It doesn't handle passwords or account credentials.

Build complex reasoning pipelines with LangChain using our Todoist MCP Server.

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 LangChain

Create your Vinkius account to connect Todoist to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-step Task Management via MCP Server

The `list_tasks` tool lets you pull a list of active tasks, and then you can pass the resulting project IDs into the `list_projects` tool. This chain helps you narrow down exactly what needs attention without manual searching. You build full pipelines where your agent figures out which task lists it needs to check first, then pulls related sections via `list_sections`, all in one go.

Automated Task Creation with LangChain

Need a new item added? You use the `create_task` tool. It handles giving the task content and even takes an optional project ID, keeping everything organized right away. This is great for workflows where one step generates data that immediately needs to become a tracked action in Todoist.

Deep Project Discovery

Start by calling `list_projects` to see every active container. Once you know the project ID, you can drill down using `list_sections` to map out the sub-areas within it. This lets your agent understand the full structure of your Todoist setup before trying to find a specific task.

Setup guide

Set up Todoist MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Todoist tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "todoist-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Todoist transactions"
    })
    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 LangChain

You start by calling `list_tasks`. You can filter that list right away if you know the project ID, which saves time. The agent handles running those filters automatically.

Yep. Just tell your AI client to use `create_task`. You provide the content and optionally point it toward a project ID so it lands exactly where you want it.

The MCP Server exposes multiple tools, like `list_comments` or `list_labels`. Your agent calls these sequential steps to gather all necessary task metadata before you even start analyzing it.

Absolutely. The `list_projects` tool pulls every active project ID, giving your chain the full scope of what's available to work with.

This server touches task metadata, including the `project_id` and general `task content`. It doesn't handle passwords or account credentials.

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