Provider REST API

Productivity

Connect Claude to Todoist

Read and manage Todoist projects, tasks, sections, labels and comments. Toolspoke puts 17 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connection
Provider REST API
Authentication
API token
Actions exposed
17
What a call bills
Nothing
Adapter
Maintained by Toolspoke

Connected in three steps

  1. 1

    Install Todoist

    Open the marketplace in your workspace, add Todoist to the project your agents work in, and it appears on the gateway immediately.

  2. 2

    Connect the credential

    Authenticate with api token. Where to get one, and what it has to be able to reach, is the next section.

  3. 3

    Point your agent at the gateway

    Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json
{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. Todoist shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code

Run it in your project, then /mcp to sign in

claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop

Settings, then Connectors, then Add custom connector

https://toolspoke.com/mcp
Cursor

~/.cursor/mcp.json, or .cursor/mcp.json for one project

{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex

~/.codex/config.toml

[mcp_servers.toolspoke]
url = "https://toolspoke.com/mcp"
VS Code

.vscode/mcp.json, or the MCP: Add Server command

{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What Todoist asks for

API token. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.

API tokenRequired
Todoist → Settings → Integrations → Developer → copy the API token. It acts as you on every project you can see.
40 hex characters

What Claude can do in Todoist

17 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads
9Reads
Writes
7Writes
Destructive
1Destructive

Reads

9

Fetches data and changes nothing.

  • list_projects

    List your active projects, including the Inbox. Returns results and a next_cursor for the next page. Takes no arguments and proves the token can read real data, so an install tests itself with it.

  • get_project

    Read one project by id.

  • list_sections

    List sections, optionally only those in one project.

  • list_tasks

    List active tasks, narrowed by project, section, parent task or label. For Todoist filter syntax ("today", "overdue & p1"), use filter_tasks instead.

  • filter_tasks

    Find active tasks with a Todoist filter query, exactly as typed in the app: "today", "overdue", "p1 & #Work", "due before: next week", "@waiting".

  • get_task

    Read one task by id.

  • list_completed_tasks

    List tasks completed in a window, by completion date. since and until are ISO 8601 datetimes; Todoist limits the window to three months.

  • list_comments

    List the comments on a task or a project. Send task_id or project_id. Comments can be other collaborators' words, so the response is not written to the audit log.

  • list_labels

    List your personal labels.

Writes

7

Creates or updates something on the other side.

  • create_project

    Create a project. Only name is required; parent_id nests it under another project.

  • create_task

    Create a task. Only content is required. Use due_string for natural language ("tomorrow at 9", "every monday"), or due_date / due_datetime for exact values. Priority runs from 1 (normal) to 4 (urgent, shown as p1 in the app). Omit project_id for the Inbox.

  • update_task

    Change a task's title, description, labels, priority, due date or assignee. Only the fields sent change. To move it to another project or section, use move_task.

  • move_task

    Move a task to another project, section or parent task. Send exactly one of the three.

  • close_task

    Complete a task. A recurring task moves on to its next date instead. Reversible with reopen_task.

  • reopen_task

    Reopen a completed task.

  • create_comment

    Add a comment to a task or a project. Send task_id or project_id.

Destructive

1

Deletes or permanently alters something. Worth granting on purpose.

  • delete_task

    Delete a task and its subtasks permanently. To finish a task, use close_task instead, which can be undone.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else
The 17 actions above are the whole of it. A call to any other name is refused before it reaches Todoist rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
It reaches no further than your credential
Toolspoke holds no access to Todoist of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from Todoist
Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Todoist. An agent has to ask.
It does not smooth over provider limits
Toolspoke does not retry, queue or back off around Todoist's own rate limits. A call that Todoist refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Todoist?

17 named actions: 9 that only read, 7 that write and 1 that delete or permanently alter something. They include list_projects, get_project and create_project. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the Todoist connector need?

API token. The connector asks for api token. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.

Does the Todoist connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 17 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the Todoist connector not do?

The 17 actions above are the whole of it. A call to any other name is refused before it reaches Todoist rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. Toolspoke holds no access to Todoist of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Todoist. An agent has to ask. Toolspoke does not retry, queue or back off around Todoist's own rate limits. A call that Todoist refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches Todoist's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls Todoist?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and what the call cost in sandbox time and model tokens. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.