Toggl Track connector for AI agents

Tools your time tracking agent reaches for on Toggl Track, scoped per user.

CALL ANY TOOL

44 tools for time tracking in Toggl Track: create, update, and stop time entries, manage projects, clients, tasks, tags, and project members, and run summary, detailed, and weekly reports.

toggl_add_project_user

Add project user

Add a workspace user to a project, optionally as manager or with a project rate. Returns the new project user with its id, project_id, user_id, manager flag, rate, and labor cost. Use this to give a user access to a private project. Use update_project_user to change an existing membership.

Parameters

Name

Type

Required

Description

project_id

integer

Required

Numeric ID of the project to add the user to. Get it from the list projects tool. Example: 203456789.

user_id

integer

Required

Numeric ID of the user to add. Get it from the list workspace users tool. Example: 5123456.

workspace_id

integer

Required

Numeric ID of the Toggl Track workspace. Get it from the list workspaces tool, or use default_workspace_id from the get current user tool. Example: 1234567.

labor_cost

number

Optional

Labor cost per hour for this user on the project (paid-plan feature). Example: 40.

labor_cost_change_mode

string

Optional

Which time entries a new labor cost applies to: start-today, override-current or override-all. Example: start-today. One of: `start-today`, `override-current`, `override-all`.

manager

boolean

Optional

Whether the user manages the project. Example: true.

rate

number

Optional

Hourly rate for this user on the project (paid-plan feature). Example: 85.

rate_change_mode

string

Optional

Which time entries a new rate applies to: start-today, override-current or override-all. Example: start-today. One of: `start-today`, `override-current`, `override-all`.

toggl_archive_client

Archive client

toggl_create_client

Create client

toggl_create_project

Create project

toggl_create_task

Create task

toggl_delete_client

Delete client

toggl_delete_project

Delete project

toggl_delete_task

Delete task

toggl_get_client

Get client

toggl_get_current_time_entry

Get current time entry

toggl_get_detailed_report

Get detailed report

Run a Toggl Track detailed report: individual time entries for a workspace in a date range, filtered by users, projects, clients, tags, tasks, or description. Returns the report rows (time entries for the detailed report, grouped when grouped is on); the reference documents no row schema, and results are paged 50 rows at a time. Use this for other users' time or long date ranges. Use get_summary_report for totals and list_time_entries for the connected user's own recent entries.

Parameters

Name

Type

Required

Description

start_date

string

Required

First day of the report, YYYY-MM-DD (inclusive, evaluated in each user's own time zone). Example: 2026-10-01.

workspace_id

integer

Required

Numeric ID of the Toggl Track workspace. Get it from the list workspaces tool, or use default_workspace_id from the get current user tool. Example: 1234567.

billable

boolean

Optional

Only include billable (true) or non-billable (false) time (paid-plan feature). Example: true.

client_ids

array

Optional

Only include time for these client IDs. Use [null] for time with no client. Example: [64123456].

description

string

Optional

Only include time entries whose description matches this text. Example: planning.

end_date

string

Optional

Last day of the report, YYYY-MM-DD (inclusive). Must be after start_date. Example: 2026-10-31.

enrich_response

boolean

Optional

Set to true to return as much detail per row as the export does. Toggl defaults to false. Example: true.

first_row_number

integer

Optional

Row number to start the page from, for pagination. Toggl returns the next value in the X-Next-Row-Number response header of the previous page. Leave empty for the first page. Example: 51.

grouped

boolean

Optional

Set to true to group similar time entries together. Toggl defaults to false. Example: true.

order_by

string

Optional

Sort field: date, user, duration, description or last_update. Toggl defaults to date. Example: duration. One of: `date`, `user`, `duration`, `description`, `last_update`.

order_dir

string

Optional

Sort direction: ASC or DESC. Example: DESC. One of: `ASC`, `DESC`.

page_size

integer

Optional

Rows per page. Toggl defaults to 50. Example: 50.

project_ids

array

Optional

Only include time on these project IDs. Use [null] for time with no project. Example: [203456789].

tag_ids

array

Optional

Only include time with these tag IDs. Use [null] for time with no tags. Example: [15234567].

task_ids

array

Optional

Only include time on these task IDs. Use [null] for time with no task. Example: [98765432].

user_ids

array

Optional

Only include time from these user IDs. Get them from the list workspace users tool. Example: [5123456].

toggl_get_project

Get project

toggl_get_project_statistics

Get project statistics

toggl_get_task

Get task

toggl_get_weekly_report

Get weekly report

toggl_list_clients

List clients

toggl_list_organization_users

List organization users

toggl_list_organizations

List organizations

toggl_list_project_users

List project users

toggl_list_projects

List projects

toggl_list_tags

List tags

toggl_list_workspace_tasks

List workspace tasks

toggl_list_workspace_users

List workspace users

toggl_remove_project_user

Remove project user

toggl_restore_client

Restore client

toggl_stop_time_entry

Stop time entry

toggl_update_client

Update client

toggl_update_project

Update project

toggl_update_tag

Update tag

toggl_update_task

Update task

For more tools, view docs.

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Toggl Track tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["toggl"], toolNames: [
    "toggl_list_projects",
    "toggl_create_time_entry",
    "toggl_stop_time_entry"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Start a timer for Client call on the Acme project" }] });

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

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["toggl"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Start a timer for Client call on the Acme project" }],
  tools,
});

// Execute the tool call with the user's vaulted Toggl Track API token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

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

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["toggl"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Start a timer for Client call on the Acme project" }],
  tools,
});

// Tool call runs with the user's vaulted Toggl Track API token
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["toggl"] }, pageSize: 100,
});

const agent = new Agent({
  name: "time_tracking_agent",
  model: "gemini-2.5-pro",
  instruction: "Toggl Track tools scoped to this user",
  tools,
});

await agent.run("Start a timer for Client call on the Acme project");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Toggl Track tool. Click to copy, paste into your agent, done.

Time entries

Copy the prompt

Copied

Start a timer for Client call on the Acme project.

Copy the prompt

Copied

Stop my running time entry.

Copy the prompt

Copied

List my time entries from yesterday.

Projects

Copy the prompt

Copied

Create a project called Website Relaunch for the client Acme.

Copy the prompt

Copied

Add Sam to the Website Relaunch project as a manager.

Copy the prompt

Copied

Archive the client Globex and its projects.

Reports

Copy the prompt

Copied

Run a summary report of hours by project for last month.

Copy the prompt

Copied

Show a weekly report of tracked time per user.

Copy the prompt

Copied

List every time entry on the Acme project this week with descriptions.

SEE HOW AUTH WORKS

Each user connects their own Toggl Track API token once, and Scalekit sends it with every call. API tokens stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Toggl Track

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

Store

Their

Toggl Track

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

Resolve

When your agent calls a

Toggl Track

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

Audit

Every

Toggl Track

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

See the same per-user auth pattern across other time tracking and project management connectors.

Engineering Teams

Engineering standup agent

Pulls commits from GitHub and GitLab, tracks issue movement in Jira, and posts a per-engineer standup brief to Slack. Each engineer's activity is read on their own delegated OAuth.

Engineering Teams

Slack triage

Polls Slack for new messages, classifies bugs and support requests with a LangGraph router, files GitHub issues or Zendesk tickets, and confirms in the thread.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Toggl Track API token looks fine in a demo. In production every time entry the agent starts or stops looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Toggl Track today. Ten connectors 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 Toggl Track as the user or through a shared API token?

As the user. Each user connects their own Toggl Track API token once, and Scalekit sends it with every call. Tools such as toggl_list_time_entries return that user's own time entries, and audit logs attribute every action to that user, not a shared service account.

Where are the Toggl Track credentials stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate them, the user reconnects with a new API token. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Toggl Track?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example the report and list tools without toggl_delete_time_entry, which deletes a time entry permanently, or toggl_delete_project. Scalekit also enforces scope checks before every API call.

What happens when Toggl Track access is turned off?

Disable the connection in the Scalekit dashboard and the next tool call fails closed with a clear error. Other tenants are unaffected, and the change is logged.

Which Toggl Track workspaces can the agent reach?

The workspaces and organizations the connected user belongs to. toggl_list_workspaces and toggl_list_organizations return them, and the project, client, tag, and report tools take a workspace ID.