MCP & AI Agent Integration

Toggl
automation.

21 AI agent actions for Toggl — callable from any MCP-compatible runtime, Claude, Cursor, or Cerebral OS workflow. Use Toggl to log time, track project hours, and generate utilization reports automatically. Full governance, audit trail, and dry-run safety on every execution.

No credit card required
Live in production environments
<200ms median execution
Dry-run before production
Execution trace
live
21
actions
100%
governed
<200ms
latency
21
AI agent actions
10
Read operations
11
Write operations
3
High-risk actions (approval gated)
Time Tracking Toggl is a Time Tracking integration — use it to automate time tracking, project hours, and team utilization from any AI agent or MCP-compatible runtime.
Actions

What you can do
with Toggl.

Every action below is available as an MCP tool and a verb in Cerebral OS — callable from any AI agent, Claude, Cursor, Windsurf, or your own runtime via the BYOA API. All executions are governed, audited, and dry-run safe.

Get Client
toggl:get_client
Fetch a single client by ID with basic details.
Read Low risk
Get Current Time Entry
toggl:get_current_time_entry
Get the currently running time entry for the authenticated user.
Read Low risk
Get Project
toggl:get_project
Fetch a single project by ID with details like client, color, and status.
Read Low risk
Get Time Entry
toggl:get_time_entry
Fetch a single time entry by ID with project, task, and duration details.
Read Low risk
Get User
toggl:get_user
Get the authenticated user's profile information.
Read Low risk
Get Workspace
toggl:get_workspace
Fetch a single workspace by ID with basic details.
Read Low risk
List Clients
toggl:list_clients
List clients in a workspace with optional filter for archived status.
Read Low risk
List Projects
toggl:list_projects
List projects in a workspace with optional filters for active status and client.
Read Low risk
List Time Entries
toggl:list_time_entries
List time entries with optional date range and project filters.
Read Low risk
List Workspaces
toggl:list_workspaces
List all workspaces the authenticated user has access to.
Read Low risk
Create Client
toggl:create_client
Create a new client in a workspace.
Write Medium risk
Create Project
toggl:create_project
Create a new project in a workspace.
Write Medium risk
Create Time Entry
toggl:create_time_entry
Create a new time entry. Can be started immediately or created as a completed entry with duration.
Write Medium risk
Delete Client
toggl:delete_client
Delete a client permanently. This action cannot be undone and will affect associated projects.
Write High risk
Delete Project
toggl:delete_project
Delete a project permanently. This action cannot be undone.
Write High risk
Delete Time Entry
toggl:delete_time_entry
Delete a time entry permanently. This action cannot be undone.
Write High risk
Start Time Entry
toggl:start_time_entry
Start a new time entry that will run until stopped. This stops any currently running timer.
Write Medium risk
Stop Time Entry
toggl:stop_time_entry
Stop a running time entry by setting the stop time to now.
Write Low risk
Update Client
toggl:update_client
Update an existing client's properties.
Write Medium risk
Update Project
toggl:update_project
Update an existing project's properties.
Write Medium risk
Update Time Entry
toggl:update_time_entry
Update an existing time entry's properties.
Write Medium risk
MCP & Runtime API

Call Toggl
from any AI agent.

Any AI agent — Claude, Cursor, LangChain, AutoGen, or your own — can call Toggl actions through the Cerebral OS Runtime API. Governance, credentials, and audit trail fire automatically.

toggl:get_client READ
# Call via Runtime API
curl
-X POST \
  "https://api.cerebralos.com/v1/runtime/actions/run"
  -H "X-API-Key: YOUR_KEY" \
  -d '{
    "verb": "toggl:get_client",
    "args": {},
    "execution_id": "agent-001"
  }'
toggl:create_client WRITE
# Dry-run first — no production risk
curl
-X POST \
  "https://api.cerebralos.com/v1/runtime/actions/run"
  -H "X-API-Key: YOUR_KEY" \
  -d '{
    "verb": "toggl:create_client",
    "args": {},
    "execution_id": "agent-001",
    "metadata": {"dryRun": true}
  }'
Get your Runtime API key at app.cerebralos.com/signup — 1,000 free executions, no credit card required.
AI agent examples

What your AI agent
can do with Toggl.

Real patterns your AI agent can execute via MCP or the Runtime API. Every action governed, dry-run safe, and fully audited.

Trigger
AI agent needs Toggl data
Call toggl:get_client via MCP or Runtime API
AI processes result and takes next action
Full execution logged to audit trail automatically
Trigger
Workflow needs to write to Toggl
Dry-run validates toggl:create_client before execution
Approval gate fires if risk level is high
Action executes with full governance — logged, audited, reversible
Trigger
Event in Toggl
Process with AI agent
Take governed action
Log to audit trail
How it works

Every Toggl action
governed end-to-end.

Cerebral OS isn't a connector. It's the execution layer that sits in front of Toggl — adding governance, dry-run safety, and a full audit trail to every operation.

Governance first
Every verb carries a risk classification. High-risk writes require explicit approval gates before they execute in production.
Dry-run safe
Simulate any Toggl action before it touches production. See exactly what would happen before a single real call is made.
Immutable audit trail
Every Toggl action is logged — what ran, what changed, who approved it, when it happened. Full history on every verb, forever.
Connect with

Toggl works best
alongside these.

Build multi-step workflows that connect Toggl to the rest of your stack. All governed. All audited.

Toggl integration

Start free.
No credit card required.

Start free with 1,000 runs — no credit card required. Connect Toggl in minutes, dry-run every action before it touches production, full audit trail on everything.

Start free — 1,000 runs Browse all integrations →