Todoist MCP connector for AI agents

CALL ANY TOOL

Manage tasks, projects, labels, and filters in Todoist. Same toolkit, every framework, no auth plumbing.

todoist_tasks_list

List tasks

List tasks with optional filters for project, label, priority, due date, and completion status.

Parameters

Name

Type

Required

Description

project_id

string

Optional

Filter by project ID

label

string

Optional

Filter by label name

priority

integer

Optional

Filter by priority: 1 (urgent), 2 (high), 3 (medium), 4 (normal)

filter

string

Optional

Todoist filter expression (e.g. today, overdue, #ProjectName)

todoist_task_create

Create task

todoist_projects_list

List projects

todoist_labels_list

List labels

todoist_task_complete

Complete task

Build your Agent

Drop the toolkit in, point it at the user, and your agent can manage Todoist tasks and projects from the first run.

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["todoistmcp"], toolNames: ["todoist_tasks_list", "todoist_task_create", "todoist_task_complete"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["todoistmcp"], toolNames: ["todoist_tasks_list", "todoist_task_create", "todoist_task_complete"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["todoistmcp"], toolNames: ["todoist_tasks_list", "todoist_task_create", "todoist_task_complete"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/todoistmcp",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your productivity agent to start managing Todoist tasks.

Search & recall

Copy the prompt

Copied

List all priority-1 tasks due this week.

Copy the prompt

Copied

Show all overdue tasks in my Todoist.

Copy the prompt

Copied

List all tasks labeled [label] across all projects.

Action & create

Copy the prompt

Copied

Create a task: [title] due [date] with priority [1] in [project].

Copy the prompt

Copied

Mark task [ID] as complete.

Copy the prompt

Copied

List all projects in my Todoist and their task counts.

SEE HOW AUTH WORKS

Users authorize Todoist once. Their credentials stay vaulted, every task action runs under their identity, and every call is logged.

1

Authorize

Your user connects

Todoist MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

Todoist MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

Todoist MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

Todoist MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Same per-user auth pattern across other productivity and project management connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Todoist MCP today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Todoist as the user or a shared account?

As the user. Each person authorizes once and all task actions are attributed to that user's Todoist account.

Where is the Todoist OAuth token stored?

In Scalekit's AES-256 vault, namespaced per tenant. Tokens never appear in prompts or LLM context.

Can I restrict the agent to read-only task access?

Yes. Use listScopedTools to allow task listing without granting creation or completion.

What happens when a user revokes Todoist access?

The connection is invalidated on the next tool call. Subsequent requests fail closed.

Can the agent create Todoist tasks from Slack messages in one workflow?

Yes. A single agent can read Slack messages and create Todoist tasks in the same workflow, using the same user identity.

Todoist MCP

Tools your agent reaches for on Todoist MCP, scoped per user.