Product and engineering

The Todoist connector.

Projects, tasks and comments. Connect once with your own key. Every agent your team runs reads the same 6 tools under one permission model.

How access is governed

6

Read tools

Open by default. They run when called, and every call is logged with the endpoint, tool and capability.

0

Write tools

Todoist exposes no write tools. Nothing it does mutates external state.

0

Destructive tools

Todoist defines no destructive tools. Nothing here deletes data.

Defaults come from the capability on each tool definition, and an admin can tighten or open any tool individually. The endpoint's capability ceiling can only tighten that policy. An endpoint scoped to read never surfaces a write tool.

Every Todoist tool

6 tools, named as the agent sees them.

  • list_projectsread

    List Todoist projects. Start here — list_tasks and list_sections both filter by a project_id from this list.

  • list_tasksread

    List active (uncompleted) tasks, optionally narrowed to one project, section or label. Ids come from list_projects and list_sections. For anything date-based ("today", "overdue") use filter_tasks instead.

  • filter_tasksread

    Find tasks with Todoist's filter language — the way to answer date and cross-project questions. Examples: 'today', 'overdue', '7 days & @work', 'p1 & #Marketing', 'assigned to: me'.

  • get_taskread

    Get one task with its full description. Takes a task id from list_tasks or filter_tasks.

  • list_sectionsread

    List the sections (columns) inside a project, so tasks can be grouped the way the board shows them.

  • list_commentsread

    List the comment thread on one task or one project. Pass exactly one of task_id or project_id — the API rejects the call with neither.

Use it from any agent

The same Todoist tools reach Claude Code, Cursor, Claude Desktop or your own agent through one MCP endpoint. The endpoint is scoped to a group, the token is issued per group and revocable from the dashboard, and an allowed-tool list and capability ceiling limit what it exposes. Reads run. Gated writes refuse unless an admin opens them. Destructive tools remain unavailable over MCP.

.mcp.json · works for Cursor and Claude Desktop too
{
  "mcpServers": {
    "growth": {
      "type": "http",
      "url": "https://app.notara.ai/mcp/g/acme/growth",
      "headers": {
        "Authorization": "Bearer ntr_mcp_xxxxxxxxxxxxxxxxxxxx"
      }
    }
  }
}

The URL and token are placeholders. Real endpoints are issued per group from the dashboard.

Setup

  1. 01

    Create a Todoist API Token in your Todoist account (where to find it). The key is yours: Notara stores it encrypted and never sees a bill.

  2. 02

    Paste it into the Notara dashboard. Credentials can be scoped to the workspace or to one person.

  3. 03

    The tools appear with their capability defaults already set. Tighten or open any of them per tool, then invite the agent to a channel or issue an MCP token.

More in product and engineering

LinearCursorSentryAsanaClickUpNotion

Connect Todoist once. Use it everywhere.

Use Notara directly, or bring us the workflow that needs to be redesigned and built.

Book a callSign in